* Re: sis190
@ 2005-06-15 15:22 Pascal CHAPPERON
2005-06-16 22:34 ` sis190 Francois Romieu
0 siblings, 1 reply; 27+ messages in thread
From: Pascal CHAPPERON @ 2005-06-15 15:22 UTC (permalink / raw)
To: Francois Romieu; +Cc: Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
> Message du 14/06/05 22:06
> De : "Francois Romieu" <romieu@fr.zoreil.com>
> The patch of the day uses a 4 bytes aligned Rx buffer address (at least for
> the usual MTU) and copies the Rx data. Can you reproduce the usual testing
> and tell if it makes a difference ?
>
> Patch available at:
> http://www.fr.zoreil.com/people/francois/misc/20050614-2.6.12-rc-sis190-test.patch
>
> --
> Ueimor
>
# cat /var/log/messages
[...]
Jun 15 15:24:37 local kernel: sis190 Gigabit Ethernet driver 1.2 loaded
Jun 15 15:24:37 local kernel: ACPI: PCI Interrupt 0000:00:04.0[A] -> Link [LNKD] -> GSI 11 (level, low) -> IRQ 11
Jun 15 15:24:37 local kernel: 0000:00:04.0: sis190 at ffffc20000004c00 (IRQ: 11), 00:11:2f:e9:42:70
Jun 15 15:24:37 local kernel: eth0: Enabling Auto-negotiation.
Jun 15 15:24:37 local kernel: eth0: status = 63000000
Jun 15 15:24:37 local kernel: eth0: status = 20000000
Jun 15 15:24:38 local last message repeated 109 times
Jun 15 15:24:38 local kernel: eth0: status = 22000000
Jun 15 15:24:39 local kernel: eth0: status = 20000000
Jun 15 15:24:39 local last message repeated 48 times
Jun 15 15:24:39 local network: Bringing up interface eth0: succeeded
Jun 15 15:24:39 local kernel: eth0: status = 20000000
Jun 15 15:24:47 local last message repeated 606 times
Jun 15 15:24:47 local kernel: eth0: mii 0x1f = 0000.
Jun 15 15:24:47 local kernel: eth0: mii lpa = 45e1.
Jun 15 15:24:47 local kernel: eth0: Link on 1000 Mbps Full Duplex mode.
Jun 15 15:24:47 local kernel: eth0: status = 20000000
Jun 15 15:25:18 local last message repeated 2361 times
[...]
Jun 15 15:26:56 local kernel: eth0: Rx status = 400c0040
Jun 15 15:26:56 local kernel: eth0: Rx PSize = 01010040
Jun 15 15:26:56 local kernel: sk_buff[0]->tail = ffff81001f2bd814
Jun 15 15:26:56 local kernel: eth0: Rx status = c0000000
[...]
Jun 15 15:26:57 local kernel: eth0: Rx status = 400c0040
Jun 15 15:26:57 local kernel: eth0: Rx PSize = 01010040
Jun 15 15:26:57 local kernel: sk_buff[0]->tail = ffff81001ef4c014
Jun 15 15:26:57 local kernel: eth0: Rx status = c0000000
[...]
# ifconfig
eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
inet addr:10.169.21.20 Bcast:10.169.23.255 Mask:255.255.252.0
inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:0 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:0 (0.0 b) TX bytes:0 (0.0 b)
Interrupt:11 Base address:0xdead
# ping -c 1 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 56(84) bytes of data.
>From 10.169.21.20 icmp_seq=0 Destination Host Unreachable
--- 10.169.21.1 ping statistics ---
1 packets transmitted, 0 received, +1 errors, 100% packet loss, time 0ms
#tcpdump -enx [local]
15:30:56.690828 00:11:2f:e9:42:70 > Broadcast, ethertype ARP (0x0806), length 42: arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
15:30:56.691065 48:6e:08:06:00:01 > 42:70:00:30:4f:06, ethertype IPv4 (0x0800), length 60: IP0 bad-len 2
0x0000: 0604 0002 0030 4f06 486e 0aa9 1501 0011 .....0O.Hn......
0x0010: 2fe9 4270 0aa9 1514 0000 0000 0000 0000 /.Bp............
0x0020: 0000 0000 0000 0000 0000 0c15 4f3d ............O=
15:30:57.690671 00:11:2f:e9:42:70 > Broadcast, ethertype ARP (0x0806), length 42: arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
15:30:57.690840 48:6e:08:06:00:01 > 42:70:00:30:4f:06, ethertype IPv4 (0x0800), length 60: IP0 bad-len 2
0x0000: 0604 0002 0030 4f06 486e 0aa9 1501 0011 .....0O.Hn......
0x0010: 2fe9 4270 0aa9 1514 0000 0000 0000 0000 /.Bp............
0x0020: 0000 0000 0000 0000 0000 0c15 4f3d ............O=
15:30:58.690519 00:11:2f:e9:42:70 > Broadcast, ethertype ARP (0x0806), length 42: arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
15:30:58.690691 48:6e:08:06:00:01 > 42:70:00:30:4f:06, ethertype IPv4 (0x0800), length 60: IP0 bad-len 2
0x0000: 0604 0002 0030 4f06 486e 0aa9 1501 0011 .....0O.Hn......
0x0010: 2fe9 4270 0aa9 1514 0000 0000 0000 0000 /.Bp............
0x0020: 0000 0000 0000 0000 0000 0c15 4f3d ............O=
# ping -c 1 -s 250 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 250(278) bytes of data.
>From 10.169.21.20 icmp_seq=0 Destination Host Unreachable
--- 10.169.21.1 ping statistics ---
1 packets transmitted, 0 received, +1 errors, 100% packet loss, time 0ms
#tcpdump -enx [local]
15:32:44.705404 00:11:2f:e9:42:70 > Broadcast, ethertype ARP (0x0806), length 42: arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
15:32:44.705641 48:6e:08:06:00:01 > 42:70:00:30:4f:06, ethertype IPv4 (0x0800), length 60: IP0 bad-len 2
0x0000: 0604 0002 0030 4f06 486e 0aa9 1501 0011 .....0O.Hn......
0x0010: 2fe9 4270 0aa9 1514 0000 0000 0000 0000 /.Bp............
0x0020: 0000 0000 0000 0000 0000 0c15 4f3d ............O=
15:32:45.705250 00:11:2f:e9:42:70 > Broadcast, ethertype ARP (0x0806), length 42: arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
15:32:45.705442 48:6e:08:06:00:01 > 42:70:00:30:4f:06, ethertype IPv4 (0x0800), length 60: IP0 bad-len 2
0x0000: 0604 0002 0030 4f06 486e 0aa9 1501 0011 .....0O.Hn......
0x0010: 2fe9 4270 0aa9 1514 0000 0000 0000 0000 /.Bp............
0x0020: 0000 0000 0000 0000 0000 0c15 4f3d ............O=
15:32:46.705098 00:11:2f:e9:42:70 > Broadcast, ethertype ARP (0x0806), length 42: arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
15:32:46.705325 48:6e:08:06:00:01 > 42:70:00:30:4f:06, ethertype IPv4 (0x0800), length 60: IP0 bad-len 2
0x0000: 0604 0002 0030 4f06 486e 0aa9 1501 0011 .....0O.Hn......
0x0010: 2fe9 4270 0aa9 1514 0000 0000 0000 0000 /.Bp............
0x0020: 0000 0000 0000 0000 0000 0c15 4f3d ............O=
# i tried to remove NET_IP_ALIGN :
# diff -puN sis190-20050614.c sis190.c
--- sis190-20050614.c 2005-06-15 16:39:08.000000000 +0200
+++ sis190.c 2005-06-15 16:41:28.000000000 +0200
@@ -405,11 +405,10 @@ static int sis190_alloc_rx_skb(struct pc
* To be verified: the asic only DMA to a four bytes aligned address
* -> the usual NET_IP_ALIGN margin must be increased by a 2x factor.
*/
- skb = dev_alloc_skb(rx_buf_sz + 2*NET_IP_ALIGN);
+ skb = dev_alloc_skb(rx_buf_sz);
if (!skb)
goto err_out;
- skb_reserve(skb, 2*NET_IP_ALIGN);
*sk_buff = skb;
mapping = pci_map_single(pdev, skb->tail, rx_buf_sz,
@@ -456,10 +455,8 @@ static inline int sis190_try_rx_copy(str
if (pkt_size < rx_copybreak) {
struct sk_buff *skb;
-
- skb = dev_alloc_skb(pkt_size + NET_IP_ALIGN);
+ skb = dev_alloc_skb(pkt_size);
if (skb) {
- skb_reserve(skb, NET_IP_ALIGN);
printk(KERN_INFO "sk_buff[0]->tail = %p\n",
sk_buff[0]->tail);
eth_copy_and_sum(skb, sk_buff[0]->tail, pkt_size, 0);
@@ -468,9 +465,6 @@ static inline int sis190_try_rx_copy(str
ret = 0;
}
}
- /* Fix the IP align issue by hand. */
- if (ret < 0)
- sis190_align(sk_buff[0], pkt_size);
return ret;
}
It seemed to work : ping, ping -s 1400, ping -s 10000.
I could even connect (a short time) on the server via ssh and work on it.
But :
# ifconfig
eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
inet addr:10.169.21.20 Bcast:10.169.23.255 Mask:255.255.252.0
inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:128 errors:0 dropped:0 overruns:0 frame:0
TX packets:82 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:158305 (154.5 KiB) TX bytes:7834 (7.6 KiB)
Interrupt:11 Base address:0xdead
Everything failed after 128 packets were received.
I tried to increase NUM_RX_DESC from 64 to 256 :
# ifconfig
eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
inet addr:10.169.21.20 Bcast:10.169.23.255 Mask:255.255.252.0
inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:512 errors:0 dropped:0 overruns:0 frame:0
TX packets:271 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:709097 (692.4 KiB) TX bytes:20284 (19.8 KiB)
Interrupt:11 Base address:0xdead
Only 512 packets were received...
Nothing special in syslog after the failure, and tcpdump reported only Tx packets :
16:18:30.891922 00:11:2f:e9:42:70 > Broadcast, ethertype ARP (0x0806), length 42: arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
I got a serious headache as i tried to understand how the RX ring works.
But it is quite too difficult for me now.
Regards
Pascal
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-15 15:22 sis190 Pascal CHAPPERON
@ 2005-06-16 22:34 ` Francois Romieu
0 siblings, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-06-16 22:34 UTC (permalink / raw)
To: Pascal CHAPPERON; +Cc: Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
Pascal CHAPPERON <pascal.chapperon@wanadoo.fr> :
[...]
> # i tried to remove NET_IP_ALIGN :
It works but the headers are not aligned any more. It could be interesting
to know what the smallest required alignment is (i.e
dev_alloc_skb(rx_buf_sz + 2^n); skb_reserve(skb, 2^n); increase n and when
the driver starts receiving again, you found it).
> But :
[...]
> Everything failed after 128 packets were received.
Can you give a try at:
http://www.fr.zoreil.com/people/francois/misc/20050616-2.6.12-rc-sis190-test.patch
Please issue a few packets, say 4 to 8, and check your log after an
ethtool -i eth0. Then wait for the Rx process to get stuck and issue
the same ethtool command. You can probably lower NUM_RX_DESC to 16 or
32 to minimize the output.
[...]
> I got a serious headache as i tried to understand how the RX ring works.
> But it is quite too difficult for me now.
The last descriptor of the Rx ring is supposed to be marked with an end
of ring indication (see RingEnd). When it is reached, the asic returns to
the start of the ring. The dirty_rx index locates the first entry in the
ring which is a candidate for refilling (assuming its Rx_skbuff entry is
equal to NULL: when a packet passes rx_copybreak, it does not generate a
hole in the ring). cur_rx locates the currently Rx DMAed buffer.
Both dirty_rx and cur_rx are meaningful % the actual number of entries in
the Rx ring, namely NUM_RX_DESC. Since NUM_RX_DESC usually is a power of
two, it is not uncommon to encounter % NUM_RX_DESC or & (NUM_RX_DESC - 1).
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
@ 2005-07-10 13:23 Pascal CHAPPERON
0 siblings, 0 replies; 27+ messages in thread
From: Pascal CHAPPERON @ 2005-07-10 13:23 UTC (permalink / raw)
To: Francois Romieu
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, lars.vahlenberg,
vinay kumar, jgarzik
> Message du 09/07/05 23:02
> De : "Francois Romieu" <romieu@fr.zoreil.com>
[...]
> Can you do the same test but send the traffic from the host which
> embeds the r8169 ?
>
> The sis190 should not be responsive during the flow. I expect that it
> will happily return to a normal state once the traffic stops.
>
Yes, no responsive at all :i could do nothing on my box during
the tests.
The second test (link partner r8169,packet_size 60, rx_copy_break 200)
froze definitly the box.
I repeated the test about 10 times after that (the station
returned to a normal state each time) :
- link partner r8169 or 8139too
- rx_copy_break 60, packet size 70
- rx_copy_break 200, packet size 60 - 70 - 200
I could not reproduce the issue...
Here is one result :
# cat /proc/net/pktgen/eth2
Params: count 10000000 min_pkt_size: 60 max_pkt_size: 60
frags: 0 delay: 0 clone_skb: 1000000 ifname: eth2
flows: 0 flowlen: 0
dst_min: 10.169.21.21 dst_max:
src_min: src_max:
src_mac: 00:40:F4:A8:70:BC dst_mac: 00:11:2F:E9:42:70
udp_src_min: 9 udp_src_max: 9 udp_dst_min: 9 udp_dst_max: 9
src_mac_count: 0 dst_mac_count: 0
Flags:
Current:
pkts-sofar: 10000000 errors: 9636478
started: 1120986879778860us stopped: 1120986948307262us idle: 14552142us
seq_num: 10000011 cur_dst_mac_offset: 0 cur_src_mac_offset: 0
cur_saddr: 0x115a90a cur_daddr: 0x1515a90a
cur_udp_dst: 9 cur_udp_src: 9
flows: 0
Result: OK: 68528402(c53976260+d14552142) usec, 10000000 (60byte,0frags)
145924pps 70Mb/sec (70043520bps) errors: 9636478
However, pktgen triggers (for all tests) thoses traces on the remote :
scheduling while atomic: pktgen.conf-1-1/0x00000001/5431
[<c02a2827>] schedule+0x947/0xbb5
[<c016ff2d>] notify_change+0x188/0x297
[<c0122750>] __mod_timer+0x124/0x15c
[<c02a3296>] schedule_timeout+0x6d/0xbb
[<c01231d1>] process_timeout+0x0/0x9
[<e0cb48f2>] count_trail_chars+0x18/0x40 [pktgen]
[<e0cb6636>] proc_thread_write+0x24c/0x2d7 [pktgen]
[<c0155b8c>] vfs_write+0xc8/0x12f
[<c0155cb2>] sys_write+0x4b/0x74
[<c0102595>] sysenter_past_esp+0x52/0x75
So i don't know if the results are significants.
(remote= P4 HT , 2.6.11.11 #3 SMP)
I also tried a ping flood from the remote :
remote # ping -q -l 256 -s 64 -f 10.169.21.21
PING 10.169.21.21 (10.169.21.21) 64(92) bytes of data.
--- 10.169.21.21 ping statistics ---
718599 packets transmitted, 718454 received, 0% packet loss, time 44313ms
rtt min/avg/max/mdev = 0.073/6.033/13.129/4.437 ms, pipe 256, ipg/ewma 0.061/7.247 ms
remote # ping -q -l 512 -s 64 -f 10.169.21.21
PING 10.169.21.21 (10.169.21.21) 64(92) bytes of data.
--- 10.169.21.21 ping statistics ---
2481376 packets transmitted, 1163044 received, 53% packet loss, time 52550ms
rtt min/avg/max/mdev = 0.065/6.945/18.312/3.045 ms, pipe 512, ipg/ewma0.021/9.369 ms
local # ifconfig
eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
inet addr:10.169.21.21 Bcast:10.169.23.255 Mask:255.255.252.0
inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:3942816 errors:0 dropped:0 overruns:0 frame:0
TX packets:2624629 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:417940801 (398.5 MiB) TX bytes:278208935 (265.3 MiB)
Interrupt:11 Base address:0xdead
> One should expect some messages to appear in the log after you forced
> the link at 10Mb/s. Do you notice anything in dmesg ?
>
Yes :
eth0: PHY reset until link up.
eth0: mii ext = 0000.
eth0: mii lpa = c1e1.
eth0: link on 100 Mbps Full Duplex mode.
> I would be interested to know if the attached patch makes a difference
> (the patch applies on top of the current driver).
>
No difference for "ethtool speed 10 duplex half autoneg off"
> Can you issue a simple 'ethtool -s eth0 autoneg off' and report what
> happens ?
>
# ethtool -s eth0 autoneg off
# ethtool eth0
[...]
Advertised auto-negotiation: No
Speed: 100Mb/s
Duplex: Full
Port: MII
PHYAD: 0
Transceiver: internal
Auto-negotiation: off
ethtool returns the same informations as long as i don't use
"ethtool -s ...".
# ethtool -s eth0 speed 10 duplex half autoneg off
# ethtool eth0
[...]
Advertised auto-negotiation: No
Speed: 10Mb/s
Duplex: Half
Port: MII
PHYAD: 0
Transceiver: internal
Auto-negotiation: off
[...]
# ethtool eth0
[...]
Advertised auto-negotiation: Yes
Speed: 100Mb/s
Duplex: Full
Port: MII
PHYAD: 0
Transceiver: internal
Auto-negotiation: on
[...]
#dmesg
[...]
eth0: PHY reset until link up.
eth0: mii ext = 0000.
eth0: mii lpa = c1e1.
eth0: link on 100 Mbps Full Duplex mode.
eth0: mii ext = 0000.
eth0: mii lpa = c1e1.
eth0: link on 100 Mbps Full Duplex mode.
---
Pascal
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-07-09 13:25 sis190 Pascal CHAPPERON
@ 2005-07-09 20:57 ` Francois Romieu
0 siblings, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-07-09 20:57 UTC (permalink / raw)
To: Pascal CHAPPERON
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, lars.vahlenberg,
vinay kumar, jgarzik
[-- Attachment #1: Type: text/plain, Size: 3309 bytes --]
Pascal CHAPPERON <pascal.chapperon@wanadoo.fr> :
[...]
> I don't receive Lars's results, but here are my results.
Lars can apparently not reproduce it any more. I'll consider this
issue fixed until it returns. Thanks for checking.
[ping test removed]
> # cat /proc/net/pktgen/eth0
> Params: count 10000000 min_pkt_size: 60 max_pkt_size: 60
> frags: 0 delay: 0 clone_skb: 1000000 ifname: eth0
> flows: 0 flowlen: 0
> dst_min: 10.169.21.1 dst_max:
> src_min: src_max:
> src_mac: 00:11:2F:E9:42:70 dst_mac: 00:40:F4:A8:70:BC
> udp_src_min: 9 udp_src_max: 9 udp_dst_min: 9 udp_dst_max: 9
> src_mac_count: 0 dst_mac_count: 0
> Flags: IPDST_RND
> Current:
> pkts-sofar: 8699475 errors: 0
> started: 1120913419217947us stopped: 1120913484497743us idle: 0us
> seq_num: 8699485 cur_dst_mac_offset: 0 cur_src_mac_offset: 0
> cur_saddr: 0x1515a90a cur_daddr: 0x115a90a
> cur_udp_dst: 9 cur_udp_src: 9
> flows: 0
> Result: OK: 65279796(c65279796+d0) usec, 8699475 (60byte,0frags)
> 133264pps 63Mb/sec (63966720bps) errors: 0
Not too bad: it trashes data fast enough :o)
Can you do the same test but send the traffic from the host which
embeds the r8169 ?
The sis190 should not be responsive during the flow. I expect that it
will happily return to a normal state once the traffic stops.
If it behaves correctly, I'll send a first version for inclusion.
> "ethtool -s eth0 ..." does not freeze the station anymore, but
> "autoneg off" does not work properly :
>
> # ethtool -s eth0 speed 10 duplex half autoneg off
> # ethtool eth0
> Settings for eth0:
> Supported ports: [ TP MII ]
> Supported link modes: 10baseT/Half 10baseT/Full
> 100baseT/Half 100baseT/Full
> Supports auto-negotiation: Yes
> Advertised link modes: 10baseT/Half 10baseT/Full
> 100baseT/Half 100baseT/Full
> Advertised auto-negotiation: Yes
> Speed: 10Mb/s
> Duplex: Half
> Port: MII
> PHYAD: 0
> Transceiver: internal
> Auto-negotiation: on
> Current message level: 0x00000037 (55)
> Link detected: yes
> # ethtool eth0
> Settings for eth0:
> Supported ports: [ TP MII ]
> Supported link modes: 10baseT/Half 10baseT/Full
> 100baseT/Half 100baseT/Full
> Supports auto-negotiation: Yes
> Advertised link modes: 10baseT/Half 10baseT/Full
> 100baseT/Half 100baseT/Full
> Advertised auto-negotiation: Yes
> Speed: 100Mb/s
> Duplex: Full
> Port: MII
> PHYAD: 0
> Transceiver: internal
> Auto-negotiation: on
> Current message level: 0x00000037 (55)
> Link detected: yes
>
> The values written in StationControl are probaly wrong,
One should expect some messages to appear in the log after you forced
the link at 10Mb/s. Do you notice anything in dmesg ?
I would be interested to know if the attached patch makes a difference
(the patch applies on top of the current driver).
Can you issue a simple 'ethtool -s eth0 autoneg off' and report what
happens ?
[html]
Sorry, it was just a notice for Lars
--
Ueimor
[-- Attachment #2: sis190-030.patch --]
[-- Type: text/plain, Size: 648 bytes --]
Do not update StationControl after the link was forced.
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
diff -puN drivers/net/sis190.c~sis190-030 drivers/net/sis190.c
--- linux-2.6.13-rc1-gitXX/drivers/net/sis190.c~sis190-030 2005-07-09 22:11:02.381627199 +0200
+++ linux-2.6.13-rc1-gitXX-romieu/drivers/net/sis190.c 2005-07-09 22:25:37.537549276 +0200
@@ -855,7 +855,7 @@ static void sis190_phy_task(void * data)
if ((val & p->val) == p->val)
break;
}
- if (p->ctl)
+ if (!tp->mii_if.force_media && p->ctl)
SIS_W16(StationControl, p->ctl);
net_link(tp, KERN_INFO "%s: link on %s mode.\n", dev->name,
p->msg);
_
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
@ 2005-07-09 13:25 Pascal CHAPPERON
2005-07-09 20:57 ` sis190 Francois Romieu
0 siblings, 1 reply; 27+ messages in thread
From: Pascal CHAPPERON @ 2005-07-09 13:25 UTC (permalink / raw)
To: Francois Romieu
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, lars.vahlenberg,
vinay kumar, jgarzik
> Date: Wed, 6 Jul 2005 23:29:25 +0200
> From: Francois Romieu <romieu@fr.zoreil.com>
[...]
> The patchkit of the day should fix these issues:
> http://www.zoreil.com/~romieu/sis190/20050706-2.6.13-rc1/patches
[...]
> I'd appreciate if you could check the allowed frame size range, say
> ping -s 1468 ... ping -s 1473 to compare with Lars's results.
>
> You can add something like a ping -q -l 48 -s 64 -f to your tests and
> increase the 48 and NUM_{RX/TX}_DESC but I am not sure that the remote
> 8139 will be able to go terribly far. If it performs well, pktgen
> could be useful too.
I don't receive Lars's results, but here are my results.
As far as i know, they seem pretty good...
# ping -s 1468 -c2 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 1468(1496) bytes of data.
1476 bytes from 10.169.21.1: icmp_seq=0 ttl=64 time=0.762 ms
1476 bytes from 10.169.21.1: icmp_seq=1 ttl=64 time=0.638 ms
--- 10.169.21.1 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1000ms
rtt min/avg/max/mdev = 0.638/0.700/0.762/0.062 ms, pipe 2
# ping -s 1469 -c2 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 1469(1497) bytes of data.
1477 bytes from 10.169.21.1: icmp_seq=0 ttl=64 time=0.647 ms
1477 bytes from 10.169.21.1: icmp_seq=1 ttl=64 time=0.630 ms
--- 10.169.21.1 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1000ms
rtt min/avg/max/mdev = 0.630/0.638/0.647/0.026 ms, pipe 2
# ping -s 1470 -c2 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 1470(1498) bytes of data.
1478 bytes from 10.169.21.1: icmp_seq=0 ttl=64 time=0.670 ms
1478 bytes from 10.169.21.1: icmp_seq=1 ttl=64 time=0.650 ms
--- 10.169.21.1 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1000ms
rtt min/avg/max/mdev = 0.650/0.660/0.670/0.010 ms, pipe 2
# ping -s 1471 -c2 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 1471(1499) bytes of data.
1479 bytes from 10.169.21.1: icmp_seq=0 ttl=64 time=0.660 ms
1479 bytes from 10.169.21.1: icmp_seq=1 ttl=64 time=0.612 ms
--- 10.169.21.1 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1000ms
rtt min/avg/max/mdev = 0.612/0.636/0.660/0.024 ms, pipe 2
# ping -s 1472 -c2 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 1472(1500) bytes of data.
1480 bytes from 10.169.21.1: icmp_seq=0 ttl=64 time=0.655 ms
1480 bytes from 10.169.21.1: icmp_seq=1 ttl=64 time=0.637 ms
--- 10.169.21.1 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1000ms
rtt min/avg/max/mdev = 0.637/0.646/0.655/0.009 ms, pipe 2
# ping -s 1473 -c2 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 1473(1501) bytes of data.
1481 bytes from 10.169.21.1: icmp_seq=0 ttl=64 time=0.745 ms
1481 bytes from 10.169.21.1: icmp_seq=1 ttl=64 time=0.747 ms
--- 10.169.21.1 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1000ms
rtt min/avg/max/mdev = 0.745/0.746/0.747/0.001 ms, pipe 2
# ping -s 1473 -c2 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 1473(1501) bytes of data.
1481 bytes from 10.169.21.1: icmp_seq=0 ttl=64 time=0.745 ms
1481 bytes from 10.169.21.1: icmp_seq=1 ttl=64 time=0.747 ms
--- 10.169.21.1 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1000ms
rtt min/avg/max/mdev = 0.745/0.746/0.747/0.001 ms, pipe 2
NUM_TX_DESC=256
NUM_RX_DESC=256
link partner = r8169
# ping -q -l 256 -s 64 -f 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 64(92) bytes of data.
--- 10.169.21.1 ping statistics ---
2924162 packets transmitted, 2924162 received, 0% packet loss, time 143582ms
rtt min/avg/max/mdev = 0.050/3.922/116.174/10.601 ms, pipe 257, ipg/ewma 0.049/0.114 ms
# ping -q -l 512 -s 64 -f 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 64(92) bytes of data.
--- 10.169.21.1 ping statistics ---
1626523 packets transmitted, 1542700 received, 5% packet loss, time 65081ms
rtt min/avg/max/mdev = 0.050/1.167/56.088/5.896 ms, pipe 513, ipg/ewma 0.040/0.108 ms
# cat /proc/net/pktgen/eth0
Params: count 10000000 min_pkt_size: 60 max_pkt_size: 60
frags: 0 delay: 0 clone_skb: 1000000 ifname: eth0
flows: 0 flowlen: 0
dst_min: 10.169.21.1 dst_max:
src_min: src_max:
src_mac: 00:11:2F:E9:42:70 dst_mac: 00:40:F4:A8:70:BC
udp_src_min: 9 udp_src_max: 9 udp_dst_min: 9 udp_dst_max: 9
src_mac_count: 0 dst_mac_count: 0
Flags: IPDST_RND
Current:
pkts-sofar: 8699475 errors: 0
started: 1120913419217947us stopped: 1120913484497743us idle: 0us
seq_num: 8699485 cur_dst_mac_offset: 0 cur_src_mac_offset: 0
cur_saddr: 0x1515a90a cur_daddr: 0x115a90a
cur_udp_dst: 9 cur_udp_src: 9
flows: 0
Result: OK: 65279796(c65279796+d0) usec, 8699475 (60byte,0frags)
133264pps 63Mb/sec (63966720bps) errors: 0
"ethtool -s eth0 ..." does not freeze the station anymore, but
"autoneg off" does not work properly :
# ethtool -s eth0 speed 10 duplex half autoneg off
# ethtool eth0
Settings for eth0:
Supported ports: [ TP MII ]
Supported link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
Supports auto-negotiation: Yes
Advertised link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
Advertised auto-negotiation: Yes
Speed: 10Mb/s
Duplex: Half
Port: MII
PHYAD: 0
Transceiver: internal
Auto-negotiation: on
Current message level: 0x00000037 (55)
Link detected: yes
# ethtool eth0
Settings for eth0:
Supported ports: [ TP MII ]
Supported link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
Supports auto-negotiation: Yes
Advertised link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
Advertised auto-negotiation: Yes
Speed: 100Mb/s
Duplex: Full
Port: MII
PHYAD: 0
Transceiver: internal
Auto-negotiation: on
Current message level: 0x00000037 (55)
Link detected: yes
The values written in StationControl are probaly wrong,
but i really don't know what i can try...
> (on an unrelated note, something enabled the "send mail as html" checkbox
> in your mail user agent: you may consider removing it).
Sorry, but i must use Webmail, as my provider's smtp is open-relay, and i don't
how the webmail thing deals with my messages...
Regards
Pascal
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-07-06 15:58 sis190 Pascal CHAPPERON
@ 2005-07-06 21:29 ` Francois Romieu
0 siblings, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-07-06 21:29 UTC (permalink / raw)
To: Pascal CHAPPERON
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, lars.vahlenberg,
vinay kumar, jgarzik
Pascal CHAPPERON <pascal.chapperon@wanadoo.fr> :
[...]
> That one works perfectly; i tried it in the same conditions as
> the previous patch, and i don't notice a regression.
Nice.
[...]
> sis190-010.patch does not compile properly :
Point taken. Thanks.
[...]
> But i get those traces in syslog, when the driver is
> loaded and every time i use ethtool :
>
> [...]
> scheduling while atomic: mii-tool/0x00000001/4699
spinlock + msleep in __mdio_cmd()... Completely stupid.
The patchkit of the day should fix these issues:
http://www.zoreil.com/~romieu/sis190/20050706-2.6.13-rc1/patches
Tarball:
http://www.zoreil.com/~romieu/sis190/20050706-2.6.13-rc1.tar.bz2
Please shake it. You should be able to modify the set of displayed
messages with ethtool.
I'd appreciate if you could check the allowed frame size range, say
ping -s 1468 ... ping -s 1473 to compare with Lars's results.
You can add something like a ping -q -l 48 -s 64 -f to your tests and
increase the 48 and NUM_{RX/TX}_DESC but I am not sure that the remote
8139 will be able to go terribly far. If it performs well, pktgen
could be useful too.
Lars, can you describe the second host that you have used so far for
the tests:
- which nic ?
- which kernel ?
(on an unrelated note, something enabled the "send mail as html" checkbox
in your mail user agent: you may consider removing it).
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
@ 2005-07-06 15:58 Pascal CHAPPERON
2005-07-06 21:29 ` sis190 Francois Romieu
0 siblings, 1 reply; 27+ messages in thread
From: Pascal CHAPPERON @ 2005-07-06 15:58 UTC (permalink / raw)
To: Francois Romieu
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, lars.vahlenberg,
vinay kumar, jgarzik
> Message du 05/07/05 01:34
> De : "Francois Romieu" <romieu@fr.zoreil.com>
[...]
> Can you check if there is a regression in sis190-000.patch available at
> http://www.zoreil.com/~romieu/sis190/20050704-2.6.13-rc1/patches ?
>
That one works perfectly; i tried it in the same conditions as
the previous patch, and i don't notice a regression.
[...]
> If it works and you want some entertainment, you can apply sis190-010.patch
> + sis190-020.patch and experience with ethtool/mii-tool.
>
[...]
sis190-010.patch does not compile properly :
# make clean;make;make install
rm -f *.o *.ko .*.cmd .*.flags *.mod.c
make -C /lib/modules/2.6.12.1/build SUBDIRS=/data/src/sis190 modules
make[1]: Entering directory `/usr/src/linux-2.6.12.1-custom'
CC [M] /data/src/sis190/sis190.o
/data/src/sis190/sis190.c: In function `sis190_init_one':
/data/src/sis190/sis190.c:1318: error: structure has no member named `poll_controller'
# diff -puN sis190-20050704-10.c sis190.c
--- sis190-20050704-10.c 2005-07-06 14:49:19.000000000 +0200
+++ sis190.c 2005-07-06 15:41:49.000000000 +0200
@@ -639,8 +640,6 @@ static void sis190_netpoll(struct net_de
sis190_interrupt(pdev->irq, dev, NULL);
enable_irq(pdev->irq);
}
-#else
-#define sis190_netpoll NULL
#endif
static void sis190_free_rx_skb(struct sis190_private *tp,
@@ -1314,7 +1313,9 @@ static int __devinit sis190_init_one(str
dev->tx_timeout = sis190_tx_timeout;
dev->watchdog_timeo = SIS190_TX_TIMEOUT;
dev->hard_start_xmit = sis190_start_xmit;
+#ifdef CONFIG_NET_POLL_CONTROLLER
dev->poll_controller = sis190_netpoll;
+#endif
dev->set_multicast_list = sis190_set_rx_mode;
SET_ETHTOOL_OPS(dev, &sis190_ethtool_ops);
dev->irq = pdev->irq;
After that, it compiles and works as expected; i can use netconsole
and get local messages on the other box.
There is something wrong whith sis190-020.patch;
it works, i can use the link as usual, i can use
ethtool :
# ethtool eth0
Settings for eth0:
Supported ports: [ TP MII ]
Supported link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
Supports auto-negotiation: Yes
Advertised link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
Advertised auto-negotiation: Yes
Speed: 100Mb/s
Duplex: Full
Port: MII
PHYAD: 0
Transceiver: internal
Auto-negotiation: on
Current message level: 0x00000037 (55)
Link detected: yes
But i get those traces in syslog, when the driver is
loaded and every time i use ethtool :
[...]
scheduling while atomic: mii-tool/0x00000001/4699
Call Trace:<ffffffff8030358a>{schedule+122} <ffffffff801ce6de>{avc_has_perm_noaudit+1134}
<ffffffff80191290>{update_atime+64} <ffffffff80139109>{__mod_timer+425}
<ffffffff803047fe>{schedule_timeout+158} <ffffffff80139b70>{process_timeout+0}
<ffffffff80139f68>{msleep+56} <ffffffff880370c8>{:sis190:__mdio_cmd+24}
<ffffffff8803712f>{:sis190:mdio_read+15} <ffffffff88034868>{:mii:generic_mii_ioctl+152}
<ffffffff880387dd>{:sis190:sis190_ioctl+77} <ffffffff802a30db>{dev_ifsioc+971}
<ffffffff802a33e5>{dev_ioctl+741} <ffffffff802e47da>{inet_ioctl+138}
<ffffffff80297fdc>{sock_ioctl+572} <ffffffff8018967a>{do_ioctl+58}
<ffffffff8018998d>{vfs_ioctl+685} <ffffffff80189a2a>{sys_ioctl+106}
<ffffffff8010d866>{system_call+126}
[...]
scheduling while atomic: ethtool/0x00000001/4703
Call Trace:<ffffffff8030358a>{schedule+122} <ffffffff80139109>{__mod_timer+425}
<ffffffff803047fe>{schedule_timeout+158} <ffffffff80139b70>{process_timeout+0}
<ffffffff80139f68>{msleep+56} <ffffffff880370c8>{:sis190:__mdio_cmd+24}
<ffffffff8803712f>{:sis190:mdio_read+15} <ffffffff880340df>{:mii:mii_ethtool_gset+223}
<ffffffff880385de>{:sis190:sis190_get_settings+46} <ffffffff802a43d2>{dev_ethtool+290}
<ffffffff80159862>{buffered_rmqueue+690} <ffffffff80159a32>{__alloc_pages+194}
<ffffffff801ce6de>{avc_has_perm_noaudit+1134} <ffffffff801650f3>{do_no_page+483}
<ffffffff8015be4a>{__do_page_cache_readahead+362} <ffffffff8018f5eb>{__d_lookup+363}
<ffffffff801ce6de>{avc_has_perm_noaudit+1134} <ffffffff801ce6de>{avc_has_perm_noaudit+1134}
<ffffffff80191290>{update_atime+64} <ffffffff801ce76a>{avc_has_perm+90}
<ffffffff80159862>{buffered_rmqueue+690} <ffffffff801cf57a>{inode_has_perm+106}
<ffffffff801561fa>{filemap_nopage+394} <ffffffff802a33b5>{dev_ioctl+693}
<ffffffff802e47da>{inet_ioctl+138} <ffffffff80297fdc>{sock_ioctl+572}
<ffffffff8018967a>{do_ioctl+58} <ffffffff8018998d>{vfs_ioctl+685}
<ffffffff80189a2a>{sys_ioctl+106} <ffffffff8010d866>{system_call+126}
[...]
I also tried to set sis190 mode (eg: 10 full autoneg off), but the driver
froze the box.
As for now mii support seems unstable, i do not play further more with
the media management.
Regards
Pascal
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-07-02 10:52 sis190 Pascal CHAPPERON
2005-07-02 11:33 ` sis190 Francois Romieu
@ 2005-07-04 23:30 ` Francois Romieu
1 sibling, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-07-04 23:30 UTC (permalink / raw)
To: Pascal CHAPPERON
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, lars.vahlenberg,
vinay kumar, jgarzik
Pascal CHAPPERON <pascal.chapperon@wanadoo.fr> :
[...]
> I can not make other tries before Monday, but i'll take a
> look at the media management after...
>
> BTW, can you remove the following printks from the patch ?
> The printks in interrupt functions make dmesg unusuable,
> and the stuff in sis190_get_drvinfo triggers a kernel oops
> when the module is loaded (null pointer assignment).
Done.
Can you check if there is a regression in sis190-000.patch available at
http://www.zoreil.com/~romieu/sis190/20050704-2.6.13-rc1/patches ?
If it works and you want some entertainment, you can apply sis190-010.patch
+ sis190-020.patch and experience with ethtool/mii-tool.
There is a tarball as well:
http://www.zoreil.com/~romieu/sis190/20050704-2.6.13-rc1.tar.bz2
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-07-02 10:52 sis190 Pascal CHAPPERON
@ 2005-07-02 11:33 ` Francois Romieu
2005-07-04 23:30 ` sis190 Francois Romieu
1 sibling, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-07-02 11:33 UTC (permalink / raw)
To: Pascal CHAPPERON
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
Pascal CHAPPERON <pascal.chapperon@wanadoo.fr> :
[...]
> A few lines diff, and now the driver is very stable with or
> without preempted kernel...
>
> I'll be very happy if you can tell me where is the trick.
Probably:
- when it filled the last Tx descriptor sis190_start_xmit()
issued a netif_stop_queue and returned NETDEV_TX_BUSY;
- the asic completed DMAing the packet and acked it;
- sis190_tx_interrupt later released the descriptor and freed the skb;
-> since NETDEV_TX_BUSY assumes that the driver does not play with the skb,
one gets interesting results.
[...]
> I tried it carefully : console, X11 (without nvidia), X11 (with nvidia),
> IRQ sharing between sis190/nvidia, full load : it worked perfectly.
Megateuf Wayne !
[...]
> BTW, can you remove the following printks from the patch ?
> The printks in interrupt functions make dmesg unusuable,
> and the stuff in sis190_get_drvinfo triggers a kernel oops
> when the module is loaded (null pointer assignment).
I'll polish the thing and sprinkle a few netif_msg_xxx() later today.
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
@ 2005-07-02 10:52 Pascal CHAPPERON
2005-07-02 11:33 ` sis190 Francois Romieu
2005-07-04 23:30 ` sis190 Francois Romieu
0 siblings, 2 replies; 27+ messages in thread
From: Pascal CHAPPERON @ 2005-07-02 10:52 UTC (permalink / raw)
To: Francois Romieu
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
> Message du 01/07/05 01:39
> De : "Francois Romieu" <romieu@fr.zoreil.com>
[...]
>
> There is an updated version at
> http://www.zoreil.com/~romieu/sis190/20050630-2.6.13-rc1-sis190-test.patch
>
> It would be nice to know how it behaves wrt preempt (no need to experiment
> with the media management), especially if you can describe the freeze more
> specifically.
>
> --
> Ueimor
>
>
François, it's really incredible!
A few lines diff, and now the driver is very stable with or
without preempted kernel...
I'll be very happy if you can tell me where is the trick.
I tried it carefully : console, X11 (without nvidia), X11 (with nvidia),
IRQ sharing between sis190/nvidia, full load : it worked perfectly.
# uname -a
Linux local 2.6.12.1 #2 Thu Jun 23 11:05:57 CEST 2005 x86_64 x86_64 x86_64 GNU/Linux
# modinfo sis190
filename: /lib/modules/2.6.12.1/kernel/drivers/net/sis190.ko
[...]
vermagic: 2.6.12.1 preempt gcc-3.4
# cat /proc/interrupts
CPU0
0: 4403978 XT-PIC timer
1: 4594 XT-PIC i8042
2: 0 XT-PIC cascade
3: 1 XT-PIC ohci_hcd:usb3
5: 1 XT-PIC ohci_hcd:usb4
7: 7 XT-PIC ohci_hcd:usb2
8: 0 XT-PIC rtc
9: 0 XT-PIC acpi
10: 1 XT-PIC ehci_hcd:usb1
11: 18607531 XT-PIC SiS SI7012, nvidia, eth0
12: 139167 XT-PIC i8042
14: 196392 XT-PIC ide0
15: 39224 XT-PIC ide1
NMI: 2849
LOC: 4403221
ERR: 0
MIS: 0
I executed simultaneously :
- a loop within 2 TX 700MB and 1 RX 700MB
- a loop within /usr/src/linux/make clean;make
- an audio stream
- an openglx demo
- my usual tasks (mozilla, xemacs)
# ifconfig
eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
inet addr:10.169.21.21 Bcast:10.169.23.255 Mask:255.255.252.0
inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:9922052 errors:0 dropped:0 overruns:0 frame:0
TX packets:17974399 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:8064017712 (7.5 GiB) TX bytes:23410613404 (21.8 GiB)
Interrupt:11 Base address:0xdead
The average speed of the transfers was about 10MB/s under full load
without hurting too much CPU resource.
I retried the previous patch in the same conditions : it frooze the
box after a few seconds, not only with X11 (no nvidia), but also
with an audio stream (at the console).
I also retried (last patch) 10Mb/full autoneg off on the r8169 link
partner (it prevously froze the box) : it worked perfectly.
The TX performances are also improved (r8169 LP):
- 10 full autoneg off : 1,2 MB both directions
- 100 full autoneg off : 11.6MB/s both directions
It still remains a problem in half duplex modes.
Perhaps somebody else want to try the patch with different
link partners (switchs, 10Mb cards, ...)
I can not make other tries before Monday, but i'll take a
look at the media management after...
BTW, can you remove the following printks from the patch ?
The printks in interrupt functions make dmesg unusuable,
and the stuff in sis190_get_drvinfo triggers a kernel oops
when the module is loaded (null pointer assignment).
# diff -puN sis190-20050630.c sis190.c
--- sis190-20050630.c 2005-07-02 09:07:19.000000000 +0200
+++ sis190.c 2005-07-02 10:49:52.000000000 +0200
@@ -456,8 +456,6 @@ static inline int sis190_try_rx_copy(str
skb = dev_alloc_skb(pkt_size + NET_IP_ALIGN);
if (skb) {
skb_reserve(skb, NET_IP_ALIGN);
- printk(KERN_INFO "sk_buff[0]->tail = %p\n",
- sk_buff[0]->tail);
eth_copy_and_sum(skb, sk_buff[0]->tail, pkt_size, 0);
*sk_buff = skb;
sis190_give_to_asic(desc, rx_buf_sz);
@@ -483,15 +481,12 @@ static int sis190_rx_interrupt(struct ne
u32 status;
rmb();
- printk(KERN_INFO "%s: Rx status = %08x\n", dev->name,
- desc->status);
if (desc->status & OWNbit)
break;
status = le32_to_cpu(desc->PSize);
- printk(KERN_INFO "%s: Rx PSize = %08x\n", dev->name, status);
if (status & RxCRC) {
printk(KERN_INFO "%s: crc error. status = %08x\n",
@@ -638,7 +633,6 @@ static irqreturn_t sis190_interrupt(int
SIS_W32(IntrStatus, status);
- printk(KERN_INFO "%s: status = %08x\n", dev->name, status);
if ((status & LinkChange) && netif_running(dev)) {
printk(KERN_INFO "%s: link change\n", dev->name);
@@ -1230,31 +1224,11 @@ static void sis190_get_drvinfo(struct ne
struct ethtool_drvinfo *info)
{
struct sis190_private *tp = netdev_priv(dev);
- unsigned int i;
- u32 *u;
strcpy(info->driver, DRV_NAME);
strcpy(info->version, DRV_VERSION);
strcpy(info->bus_info, pci_name(tp->pci_dev));
- printk(KERN_INFO "%s: dirty_rx=%ld cur_rx=%ld\n",
- dev->name, tp->dirty_rx, tp->cur_rx);
- u = (void *) tp->RxDescRing;
- printk(KERN_INFO " PSize status addr size PSize status addr size\n");
- for (i = 0; i < (NUM_RX_DESC / 2); i++) {
- printk(KERN_INFO "%02d:%08x %08x %08x %08x %08x %08x %08x %08x\n",
- i, u[0], u[1], u[2], u[3], u[4], u[5], u[6], u[7]);
- u += 8;
- }
- printk(KERN_INFO "%s: dirty_tx=%ld cur_tx=%ld\n",
- dev->name, tp->dirty_tx, tp->cur_tx);
- u = (void *) tp->TxDescRing;
- printk(KERN_INFO " PSize status addr size PSize status addr size\n");
- for (i = 0; i < (NUM_TX_DESC / 2); i++) {
- printk(KERN_INFO "%02d %08x %08x %08x %08x %08x %08x %08x %08x\n",
- i, u[0], u[1], u[2], u[3], u[4], u[5], u[6], u[7]);
- u += 8;
- }
}
static struct ethtool_ops sis190_ethtool_ops = {
Regards
Pascal
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-26 12:39 sis190 Pascal CHAPPERON
@ 2005-06-30 23:37 ` Francois Romieu
0 siblings, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-06-30 23:37 UTC (permalink / raw)
To: Pascal CHAPPERON
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
Pascal CHAPPERON <pascal.chapperon@wanadoo.fr> :
[...]
> 1) sis190 freezes the box when kernel PREEMPT is enabled :
>
> I made many tries, but i could not solve it;
> - it does not occur while receiving huge files.
> - it does not occur when only a few packets are
> transmitted (remote connection, ls, find)
> - it occurs only while transmiting huge files AND
> trying to do someting else (open a new term,...)
> - I could transfer a huge file (700MB) several times
> as i was at the console (and i could switch to another
> console to perform find, ls,... during the transfer).
Are you saying that PREEMPT and X are both needed to freeze the box ?
If so, could you try preempt + console + rsync (+ dd from disk) ?
> I managed the system so the sis190 had its own IRQ, but it
> made no difference.
>
> As i suspected nvidia driver, i switched to nv driver : no result.
Please keep binary modules out of the loop until the things are stable.
I do not want to try and diagnose a bug in a system wherein such an amount
of unknown code was loaded (even if it was unloaded later).
> It seems to me that a task inside the sis190_tx_interrupt() is
> not protected against preemption (and it is probably the same
> on a SMP not prempted).
>
> I tried to play with spinlocks, but with no result :
> @@ -621,6 +621,7 @@ static irqreturn_t sis190_interrupt(int
> void __iomem *ioaddr = tp->mmio_addr;
> int handled = 0;
> int boguscnt;
> + unsigned long flags;
>
> for (boguscnt = max_interrupt_work; boguscnt > 0; boguscnt--) {
> u32 status = SIS_R32(IntrStatus);
> @@ -651,9 +652,9 @@ static irqreturn_t sis190_interrupt(int
> sis190_rx_interrupt(dev, tp, ioaddr);
>
> if (status & TxQ0Int) {
> - spin_lock(&tp->lock);
> + spin_lock_irqsave(&tp->lock, flags);
> sis190_tx_interrupt(dev, tp, ioaddr);
> - spin_unlock(&tp->lock);
> + spin_unlock_irqrestore(&tp->lock, flags);
Afaik the irq handler is already protected against reentrancy (see
kernel/irq.c::__do_IRQ) and softirq (see arch/xxx/kernel/irq.c::irq_exit).
So this change should not make a difference.
[...]
> @@ -581,6 +581,7 @@ static void sis190_tx_interrupt(struct n
> struct sis190_private *tp, void __iomem *ioaddr)
> {
> unsigned int tx_left, dirty_tx = tp->dirty_tx;
> + unsigned long flags;
>
> for (tx_left = tp->cur_tx - dirty_tx; tx_left > 0; tx_left--) {
> unsigned int entry = dirty_tx % NUM_TX_DESC;
> @@ -604,10 +605,12 @@ static void sis190_tx_interrupt(struct n
> dirty_tx++;
> }
>
> + spin_lock_irqsave(&tp->lock, flags);
> if (tp->dirty_tx != dirty_tx) {
> tp->dirty_tx = dirty_tx;
> netif_wake_queue(dev);
> }
> + spin_unlock_irqrestore(&tp->lock, flags);
> }
The irqsave/restore should not be needed for the same reason as above.
> In fact, i don't know where are the critical sections...
In the Tx path the critical section is related to netif_{start/stop}_queue.
> 2) sis190 freezes the box when the link partner is
> a r8169 forced in 10 full autoneg off (preempted or not
> preempted kernel) :
The r8169 driver will not necessarily do what you would expect when you
autoneg it off and it faces an unstable driver. I'll send an update for it.
Any TX timeout message on the console ? Freeze == sysrq has no effect
and keyboard leds do not blink any more ?
There is an updated version at
http://www.zoreil.com/~romieu/sis190/20050630-2.6.13-rc1-sis190-test.patch
It would be nice to know how it behaves wrt preempt (no need to experiment
with the media management), especially if you can describe the freeze more
specifically.
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
@ 2005-06-26 12:39 Pascal CHAPPERON
2005-06-30 23:37 ` sis190 Francois Romieu
0 siblings, 1 reply; 27+ messages in thread
From: Pascal CHAPPERON @ 2005-06-26 12:39 UTC (permalink / raw)
To: Francois Romieu
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, vinay kumar, jgarzik,
pascal.chapperon
> Message du 22/06/05 01:02
> De : "Francois Romieu" <romieu@fr.zoreil.com>
[...]
> I have copied the sis190 patches at http://www.zoreil.com/~romieu/sis190
> if someone wants to hack them in the meantime.
1) sis190 freezes the box when kernel PREEMPT is enabled :
I made many tries, but i could not solve it;
- it does not occur while receiving huge files.
- it does not occur when only a few packets are
transmitted (remote connection, ls, find)
- it occurs only while transmiting huge files AND
trying to do someting else (open a new term,...)
- I could transfer a huge file (700MB) several times
as i was at the console (and i could switch to another
console to perform find, ls,... during the transfer).
I managed the system so the sis190 had its own IRQ, but it
made no difference.
As i suspected nvidia driver, i switched to nv driver : no result.
It seems to me that a task inside the sis190_tx_interrupt() is
not protected against preemption (and it is probably the same
on a SMP not prempted).
I tried to play with spinlocks, but with no result :
@@ -621,6 +621,7 @@ static irqreturn_t sis190_interrupt(int
void __iomem *ioaddr = tp->mmio_addr;
int handled = 0;
int boguscnt;
+ unsigned long flags;
for (boguscnt = max_interrupt_work; boguscnt > 0; boguscnt--) {
u32 status = SIS_R32(IntrStatus);
@@ -651,9 +652,9 @@ static irqreturn_t sis190_interrupt(int
sis190_rx_interrupt(dev, tp, ioaddr);
if (status & TxQ0Int) {
- spin_lock(&tp->lock);
+ spin_lock_irqsave(&tp->lock, flags);
sis190_tx_interrupt(dev, tp, ioaddr);
- spin_unlock(&tp->lock);
+ spin_unlock_irqrestore(&tp->lock, flags);
}
}
or :
@@ -581,6 +581,7 @@ static void sis190_tx_interrupt(struct n
struct sis190_private *tp, void __iomem *ioaddr)
{
unsigned int tx_left, dirty_tx = tp->dirty_tx;
+ unsigned long flags;
for (tx_left = tp->cur_tx - dirty_tx; tx_left > 0; tx_left--) {
unsigned int entry = dirty_tx % NUM_TX_DESC;
@@ -604,10 +605,12 @@ static void sis190_tx_interrupt(struct n
dirty_tx++;
}
+ spin_lock_irqsave(&tp->lock, flags);
if (tp->dirty_tx != dirty_tx) {
tp->dirty_tx = dirty_tx;
netif_wake_queue(dev);
}
+ spin_unlock_irqrestore(&tp->lock, flags);
}
/*
@@ -651,9 +654,7 @@ static irqreturn_t sis190_interrupt(int
sis190_rx_interrupt(dev, tp, ioaddr);
if (status & TxQ0Int) {
- spin_lock(&tp->lock);
sis190_tx_interrupt(dev, tp, ioaddr);
- spin_unlock(&tp->lock);
}
}
In fact, i don't know where are the critical sections...
2) sis190 freezes the box when the link partner is
a r8169 forced in 10 full autoneg off (preempted or not
preempted kernel) :
it is probably for the same reason, as it occurs only when
transmitting a big file.
3) poor TX performances when link partner is forced to
autoneg off (not preempted kernel):
Once again it seems that something goes wrong with TX tasks...
Regards
Pascal
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-19 10:17 sis190 Pascal CHAPPERON
@ 2005-06-21 23:02 ` Francois Romieu
0 siblings, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-06-21 23:02 UTC (permalink / raw)
To: Pascal CHAPPERON
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
Pascal CHAPPERON <pascal.chapperon@wanadoo.fr> :
[...]
> I disabled PREEMPT in the kernel : the driver worked correctly.
I'll be hidden behind a 14k modem for holydays until the 30/05/2005 so
expect a low responsiveness during the upcoming week.
Of course a disk crashed just before I had to go :o/
I have copied the sis190 patches at http://www.zoreil.com/~romieu/sis190
if someone wants to hack them in the meantime.
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
@ 2005-06-19 10:17 Pascal CHAPPERON
2005-06-21 23:02 ` sis190 Francois Romieu
0 siblings, 1 reply; 27+ messages in thread
From: Pascal CHAPPERON @ 2005-06-19 10:17 UTC (permalink / raw)
To: Francois Romieu
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
> Message du 17/06/05 20:23
> De : "Francois Romieu" <romieu@fr.zoreil.com>
[...]
> It should be fixed now. Please try the patch of the day:
> http://www.fr.zoreil.com/people/francois/misc/20050617-2.6.12-rc-sis190-test.patch
>
[...]
Nice, it works :)
It is now usable, but it can freeze the box in some cases (see below).
First try : network (dhcp) initialized correctly, but the box froze
immediatly as i tried to transfer a 35MB file via scp
(not really frozen, as the transfer achieved correctly).
I had to switch power button...
i raised NUM_RX_DESC from 16 to 256 : i could achieve 2 transfers
before i lost keyboard; as i was on the console, i could see that
sis190 printks were still printed (very slowly), but nothing else
was working.
[...many tries...]
I disabled PREEMPT in the kernel : the driver worked correctly.
# modinfo sis190
[...]
alias: pci:v00001039d00000190sv*sd*bc*sc*i*
depends:
vermagic: 2.6.12-rc6 gcc-3.4
# cat /var/log/messages
[...]
Jun 18 11:04:41 local kernel: eth0: Rx status = 76040040
Jun 18 11:04:41 local kernel: eth0: Rx PSize = 01010046
Jun 18 11:04:41 local kernel: sk_buff[0]->tail = ffff81000cc78810
Jun 18 11:04:41 local kernel: eth0: Rx status = c0000000
Jun 18 11:04:41 local kernel: eth0: status = 20000004
Jun 18 11:04:41 local kernel: eth0: status = 00000040
Jun 18 11:04:41 local kernel: eth0: dirty_rx=143 cur_rx=143
Jun 18 11:04:41 local kernel: PSize status addr size PSize status addr size
Jun 18 11:04:41 local kernel: 00:00000000 c0000000 1018c010 00000600 00000000 c0000000 040a6010 00000600
Jun 18 11:04:41 local kernel: 01:00000000 c0000000 03d64010 00000600 00000000 c0000000 1ce5a010 00000600
Jun 18 11:04:41 local kernel: 02:00000000 c0000000 1ce5a810 00000600 00000000 c0000000 1179e010 00000600
Jun 18 11:04:41 local kernel: 03:00000000 c0000000 1c28f810 00000600 00000000 c0000000 1c283010 00000600
Jun 18 11:04:41 local kernel: 04:00000000 c0000000 0c863010 00000600 00000000 c0000000 0eba9010 00000600
Jun 18 11:04:41 local kernel: 05:00000000 c0000000 0eba9810 00000600 00000000 c0000000 0a24a010 00000600
Jun 18 11:04:41 local kernel: 06:00000000 c0000000 03d62010 00000600 00000000 c0000000 0cc78010 00000600
Jun 18 11:04:41 local kernel: 07:00000000 c0000000 0cc78810 00000600 01010046 76040040 040a6810 80000600
Jun 18 11:04:41 local kernel: eth0: dirty_tx=174 cur_tx=174
[...]
I also tried :
1) to comment out sis190_make_unusable_by_asic() in sis190_rx_interrupt() :
if (sis190_try_rx_copy(&skb, pkt_size, desc,
tp->rx_buf_sz)) {
pci_action = pci_unmap_single;
tp->Rx_skbuff[entry] = NULL;
/* sis190_make_unusable_by_asic(desc); */
}
No difference (it worked the same way).
2) to comment out the test "if (pkt_size < rx_copybreak)" in sis190_try_rx_copy() :
It worked with kernel PREEMPT.
The transfer speed was the same.
I imagine that rx_copybreak is better for large packets, but i still do not
understand why it is better :( (less upload ?)
> > I also tried to force 10H, 10F, 100H, 100F autoneg off on the other card.
[...]
> Did the sis190 driver report a link change event ?
>
> --
> Ueimor
>
I made new tests with 2 differents boards on the remote (modes + transfer speed) :
worked good in some cases, bad in another.
In one case (10 full with r8169) , it froze the box (see below).
I used your patch without modifications (I only remove printks to have real perfs).
NUM_TX_DESC 64
NUM_RX_DESC 256
Kernel was compiled without PREEMPT.
I transferred (twice for each test) a 35MB file in both directions.
1) local = sis190 remote = r8169
--------------------------------
remote # uname -a
Linux remote 2.6.11.11 #3 SMP Sat Jun 18 16:23:51 CEST 2005 i686 i686 i386 GNU/Linux
remote # ethtool -i eth2
driver: r8169
version: 2.2LK
remote # ethtool -s eth2 autoneg on
local # dmesg
[...]
[ 2954.467733] sis190 Gigabit Ethernet driver 1.2 loaded
[ 2954.467958] ACPI: PCI Interrupt Link [LNKD] enabled at IRQ 11
[ 2954.467961] ACPI: PCI Interrupt 0000:00:04.0[A] -> Link [LNKD] -> GSI 11 (level, low) -> IRQ 11
[ 2954.467970] PCI: Setting latency timer of device 0000:00:04.0 to 64
[ 2954.475927] 0000:00:04.0: sis190 at ffffc20000004c00 (IRQ: 11), 00:11:2f:e9:42:70
[ 2954.475932] eth0: Enabling Auto-negotiation.
[ 2954.510049] eth0: link change
[ 2954.512912] eth0: mii 0x1f = 0000.
[ 2954.514038] eth0: mii lpa = 0000.
[ 2954.514041] eth0: Link on unknown mode.
[ 2960.061387] eth0: PHY reset until link up
[ 2960.097462] eth0: no IPv6 routers present
[ 2965.614860] eth0: PHY reset until link up
[ i plug the wire ]
[ 2971.168332] eth0: PHY reset until link up
[ 2972.171635] eth0: link change
[ 2972.174572] eth0: mii 0x1f = 0000.
[ 2972.175683] eth0: mii lpa = c1e1.
[ 2972.175685] eth0: Link on 100 Mbps Full Duplex mode.
[...]
-> 35MB 11.6MB/s 00:03
<- 35MB 11.6MB/s 00:03
remote # ethtool -s eth2 speed 10 duplex half autoneg off
local # dmesg
[...]
[ 3169.769898] eth0: link change
[ 3169.773250] eth0: mii 0x1f = 0000.
[ 3169.774364] eth0: mii lpa = 4021.
[ 3169.774366] eth0: Link on 10 Mbps Half Duplex mode.
[ could not ping remote]
I had to reload sis190 (network restart was not sufficient).
-> 35MB 334.2KB/s 01:47
<- 8% 2976KB 40.2KB/s 13:35 ETA
remote # ethtool -s eth2 speed 10 duplex full autoneg off
local # dmesg
[...]
[ 3467.070750] eth0: pad error. status = 01000042
[ 3467.208669] eth0: pad error. status = 01000048
[ 3467.329894] eth0: pad error. status = 01000043
[ 3469.350736] eth0: pad error. status = 01000044
[ 3469.351500] eth0: pad error. status = 0100005a
[ 3487.685124] eth0: link change
[ 3487.687358] eth0: PHY reset until link up
[ 3488.846780] eth0: link change
[ 3488.850113] eth0: mii 0x1f = 0000.
[ 3488.851224] eth0: mii lpa = 4061.
[ 3488.851226] eth0: Link on 10 Mbps Full Duplex mode.
No need to restart network...
the transfer from local to remote froze immediatly the box.
It's always reproductible : box freshly started,
network restarted, sis190 reloaded...
-> do not try it!
<- 35MB 1.1MB/s 00:31
In the other direction (remote -> local), i could transfer
the file as many times as i wanted.
remote # ethtool -s eth2 speed 100 duplex half autoneg off
local # dmesg
[...]
[ 638.939950] eth0: link change
[ 638.943171] eth0: mii 0x1f = 0000.
[ 638.944282] eth0: mii lpa = 4081.
[ 638.944284] eth0: Link on 100 Mbps Half Duplex mode.
No need to restart network...
-> 35MB 1.0MB/s 00:35
<- 35MB 2.9MB/s 00:12
remote # ethtool -s eth2 speed 100 duplex full autoneg off
local # dmesg
[...]
[ 281.822151] eth0: link change
[ 281.825442] eth0: mii 0x1f = 0000.
[ 281.826553] eth0: mii lpa = 4181.
[ 281.826555] eth0: Link on 100 Mbps Full Duplex mode.
No need to restart network...
-> 35MB 11.6MB/s 00:03
<- 35MB 11.6MB/s 00:03
2) local = sis190 remote = 8139too
----------------------------------
remote # ethtool -i eth2
driver: 8139too
version: 0.9.27
remote # ethtool -s eth2 autoneg on
local # dmesg
[...]
[ 1122.883216] eth0: link change
[ 1122.886164] eth0: mii 0x1f = 0000.
[ 1122.887275] eth0: mii lpa = 45e1.
[ 1122.887278] eth0: Link on 100 Mbps Full Duplex mode.
No need to restart network...
-> 35MB 11.6MB/s 00:03
<- 35MB 11.6MB/s 00:03
remote # ethtool -s eth2 speed 10 duplex half autoneg off
local # dmesg
[...]
[ 1297.412384] eth0: link change
[ 1297.415299] eth0: mii 0x1f = 0000.
[ 1297.416410] eth0: mii lpa = 0021.
[ 1297.416412] eth0: Link on 10 Mbps Half Duplex mode.
No need to restart network...
-> 3% 1296KB 61.8KB/s 09:17 ETA
<- 43% 15MB 336.1KB/s 00:59 ETA
remote # ethtool -s eth2 speed 10 duplex full autoneg off
local # dmesg
[...]
[ 1396.959707] eth0: pad error. status = 01000048
[ 1396.961143] eth0: pad error. status = 0100004a
[ 1396.962580] eth0: pad error. status = 0100004a
[ 1396.964014] eth0: pad error. status = 01000042
[ 1396.965448] eth0: pad error. status = 01000042
[ 1396.966886] eth0: pad error. status = 0100004c
[ i did not find mode report ]
No need to restart network...
-> 35MB 337.3KB/s 01:46
<- 35MB 1.1MB/s 00:31
I restarted network, but nothing worked anymore; so i
also reloaded sis190.
local # dmesg
[...]
[ 1741.049314] eth0: Enabling Auto-negotiation.
[ 1746.626290] eth0: mii 0x1f = 0000.
[ 1746.627399] eth0: mii lpa = 0021.
[ 1746.627401] eth0: Link on 10 Mbps Half Duplex mode.
[false detection ^^^^]
-> 13% 4816KB 357.6KB/s 01:26 ETA
<- 35MB 1.1MB/s 00:32
remote # ethtool -s eth2 speed 100 duplex half autoneg off
local # dmesg
[...]
[ 1990.441900] eth0: link change
[ 1990.445110] eth0: mii 0x1f = 0000.
[ 1990.446222] eth0: mii lpa = 0081.
[ 1990.446224] eth0: Link on 100 Mbps Half Duplex mode.
No need to restart network...
-> 35MB 1.1MB/s 00:33
<- 35MB 2.2MB/s 00:16
remote # ethtool -s eth2 speed 100 duplex full autoneg off
local # dmesg
[...]
[ 2075.194365] eth0: pad error. statad error. status = 01000232
[...]
[ 2125.300416] eth0: pad error. status = 01000040
[ 2129.465137] eth0: pad error. status = 01000046
[ 2129.804272] eth0: pad error. status = 01000040
[ 2130.498300] eth0: pad error. status = 01000044
[ i did not find mode report ]
-> 35MB 1.2MB/s 00:30
<- 35MB 11.6MB/s 00:03
I restarted network, it worked, but still pad errors.
So i reloaded sis190.
local # dmesg
[...]
[ 2346.490911] eth0: Enabling Auto-negotiation.
[ 2352.068364] eth0: mii 0x1f = 0000.
[ 2352.069478] eth0: mii lpa = 0081.
[ 2352.069482] eth0: Link on 100 Mbps Half Duplex mode.
[false detection ^^^^]
-> 35MB 1.1MB/s 00:32
<- 35MB 11.6MB/s 00:03
As you can see, it always works fine with autoneg on, and
only 100 full with r8169 is OK with autoneg off.
Regards
Pascal
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-17 11:14 sis190 Pascal CHAPPERON
@ 2005-06-17 18:22 ` Francois Romieu
0 siblings, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-06-17 18:22 UTC (permalink / raw)
To: Pascal CHAPPERON
Cc: Juha Laiho, Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
Pascal CHAPPERON <pascal.chapperon@wanadoo.fr> :
[...]
> I noticed that you remove NET_IP_ALIGN in sis190_alloc_rx_skb(),
> but not in sis190_try_rx_copy(); though the driver "worked" like
> yesterday...
NET_IP_ALIGN should be fine in sis190_alloc_rx_skb() as it only
applies to the skb where the driver memcopies (i.e. it is not
limited by the alignement requirement of the asic).
[...]
> PSize status addr size PSize status addr size
> 00:00000000 c0000000 13381010 00000600 00000000 c0000000 13847010 00000600
> 01:00000000 c0000000 1edcb810 00000600 00000000 c0000000 1b694810 00000600
> 02:00000000 c0000000 1b697010 00000600 00000000 c0000000 077c4810 00000600
> 03:00000000 c0000000 07e15010 00000600 00000000 c0000000 06e3e810 00000600
> 04:00000000 c0000000 1719e810 00000600 00000000 c0000000 1b69b810 00000600
> 05:00000000 c0000000 1b694010 00000600 00000000 c0000000 07741010 00000600
> 06:00000000 c0000000 065d8010 00000600 00000000 c0000000 07a84010 00000600
> 07:010100a6 76040040 13381810 00000600 00000000 c0000000 1f7c1010 00000600
^ -> bug
[...]
> So i removed the test "if (pkt_size < rx_copybreak) {" in sis190_try_rx_copy.
>
> The driver now works "correctly" (ping, ssh, scp) as long as i want,
> but probably not in the way you want...
It should be fixed now. Please try the patch of the day:
http://www.fr.zoreil.com/people/francois/misc/20050617-2.6.12-rc-sis190-test.patch
> I don't understand how the Rx packets are managed when pkt_size is
> greater than rx_copybreak...
They are directly given to the upper layer. The driver tags a hole in the
Rx ring.
[...]
> I also tried to force 10H, 10F, 100H, 100F autoneg off on the other card.
> All modes were working, but obviously something was wrong :
> - 10H 0,4Mo/s both directions
> - 10F 1,2Mo/s " "
> - 100H 5Mo/s " "
> - 100F 1,2Mo/s and 0,3Mo/s
>
> For 100F, sis190 reported "100 Mbps Half Duplex" and the other card 100 Full.
Did the sis190 driver report a link change event ?
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
@ 2005-06-17 11:14 Pascal CHAPPERON
2005-06-17 18:22 ` sis190 Francois Romieu
0 siblings, 1 reply; 27+ messages in thread
From: Pascal CHAPPERON @ 2005-06-17 11:14 UTC (permalink / raw)
To: Francois Romieu; +Cc: Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
> Message du 17/06/05 00:36
> De : "Francois Romieu" <romieu@fr.zoreil.com>
>
> Can you give a try at:
> http://www.fr.zoreil.com/people/francois/misc/20050616-2.6.12-rc-sis190-test.patch
>
> Please issue a few packets, say 4 to 8, and check your log after an
> ethtool -i eth0. Then wait for the Rx process to get stuck and issue
> the same ethtool command. You can probably lower NUM_RX_DESC to 16 or
> 32 to minimize the output.
>
> --
> Ueimor
>
>
I noticed that you remove NET_IP_ALIGN in sis190_alloc_rx_skb(),
but not in sis190_try_rx_copy(); though the driver "worked" like
yesterday...
BTW, i had to put the printk about RxdescRing in sis190_interrupt(),
as i had Kernel Oops when in sis190_get_drvinfo().
# diff -puN sis190-20050616.c sis190.c
--- sis190-20050616.c 2005-06-17 11:56:46.000000000 +0200
+++ sis190.c 2005-06-17 12:12:20.000000000 +0200
@@ -76,8 +76,8 @@ static int multicast_filter_limit = 32;
/* MAC address length */
#define MAC_ADDR_LEN 6
-#define NUM_TX_DESC 64 /* Number of Tx descriptor registers */
-#define NUM_RX_DESC 64 /* Number of Rx descriptor registers */
+#define NUM_TX_DESC 16 /* Number of Tx descriptor registers */
+#define NUM_RX_DESC 16 /* Number of Rx descriptor registers */
#define TX_RING_BYTES (NUM_TX_DESC * sizeof(struct TxDesc))
#define RX_RING_BYTES (NUM_RX_DESC * sizeof(struct RxDesc))
#define RX_BUF_SIZE 1536 /* Rx Buffer size */
@@ -621,6 +621,8 @@ static irqreturn_t sis190_interrupt(int
void __iomem *ioaddr = tp->mmio_addr;
int handled = 0;
int boguscnt;
+ unsigned int i;
+ u32 *u;
for (boguscnt = max_interrupt_work; boguscnt > 0; boguscnt--) {
u32 status = SIS_R32(IntrStatus);
@@ -637,7 +639,8 @@ static irqreturn_t sis190_interrupt(int
SIS_W32(IntrStatus, status);
- printk(KERN_INFO "%s: status = %08x\n", dev->name, status);
+ if ( status != 0x20000000)
+ printk(KERN_INFO "%s: status = %08x\n", dev->name, status);
if ((status & LinkChange) && netif_running(dev)) {
printk(KERN_INFO "%s: link change\n", dev->name);
@@ -647,8 +650,29 @@ static irqreturn_t sis190_interrupt(int
if ((status & (TxQ0Int | RxQInt)) == 0)
break;
- if (status & (RxQInt))
- sis190_rx_interrupt(dev, tp, ioaddr);
+ if (status & (RxQInt)) {
+ if ( tp->cur_rx > 29) {
+ printk(KERN_INFO "%s: dirty_rx=%ld cur_rx=%ld\n",
+ dev->name, tp->dirty_rx, tp->cur_rx);
+ u = (void *) tp->RxDescRing;
+ printk(KERN_INFO " PSize status addr size PSize status addr size\n");
+ for (i = 0; i < (NUM_RX_DESC / 2); i++) {
+ printk(KERN_INFO "%02d:%08x %08x %08x %08x %08x %08x %08x %08x\n",
+ i, u[0], u[1], u[2], u[3], u[4], u[5], u[6], u[7]);
+ u += 8;
+ }
+ printk(KERN_INFO "%s: dirty_tx=%ld cur_tx=%ld\n",
+ dev->name, tp->dirty_tx, tp->cur_tx);
+ u = (void *) tp->TxDescRing;
+ printk(KERN_INFO " PSize status addr size PSize status addr size\n");
+ for (i = 0; i < (NUM_TX_DESC / 2); i++) {
+ printk(KERN_INFO "%02d %08x %08x %08x %08x %08x %08x %08x %08x\n",
+ i, u[0], u[1], u[2], u[3], u[4], u[5], u[6], u[7]);
+ u += 8;
+ }
+ }
+ sis190_rx_interrupt(dev, tp, ioaddr);
+ }
if (status & (TxQ0Int)) {
spin_lock(&tp->lock);
@@ -1233,31 +1257,11 @@ static void sis190_get_drvinfo(struct ne
struct ethtool_drvinfo *info)
{
struct sis190_private *tp = netdev_priv(dev);
- unsigned int i;
- u32 *u;
strcpy(info->driver, DRV_NAME);
strcpy(info->version, DRV_VERSION);
strcpy(info->bus_info, pci_name(tp->pci_dev));
- printk(KERN_INFO "%s: dirty_rx=%ld cur_rx=%ld\n",
- dev->name, tp->dirty_rx, tp->cur_rx);
- u = (void *) tp->RxDescRing;
- printk(KERN_INFO " PSize status addr size PSize status addr size\n");
- for (i = 0; i < (NUM_RX_DESC / 2); i++) {
- printk(KERN_INFO "%02d:%08x %08x %08x %08x %08x %08x %08x %08x\n",
- i, u[0], u[1], u[2], u[3], u[4], u[5], u[6], u[7]);
- u += 8;
- }
- printk(KERN_INFO "%s: dirty_tx=%ld cur_tx=%ld\n",
- dev->name, tp->dirty_tx, tp->cur_tx);
- u = (void *) tp->TxDescRing;
- printk(KERN_INFO " PSize status addr size PSize status addr size\n");
- for (i = 0; i < (NUM_TX_DESC / 2); i++) {
- printk(KERN_INFO "%02d %08x %08x %08x %08x %08x %08x %08x %08x\n",
- i, u[0], u[1], u[2], u[3], u[4], u[5], u[6], u[7]);
- u += 8;
- }
}
static struct ethtool_ops sis190_ethtool_ops = {
@@ -1311,6 +1315,7 @@ static int __devinit sis190_init_one(str
dev->open = sis190_open;
dev->hard_start_xmit = sis190_start_xmit;
dev->get_stats = sis190_get_stats;
+ SET_ETHTOOL_OPS(dev, &sis190_ethtool_ops);
dev->stop = sis190_close;
dev->tx_timeout = sis190_tx_timeout;
dev->set_multicast_list = sis190_set_rx_mode;
# dmesg
[...]
sis190 Gigabit Ethernet driver 1.2 loaded
ACPI: PCI Interrupt 0000:00:04.0[A] -> Link [LNKD] -> GSI 11 (level, low) -> IRQ 11
PCI: Setting latency timer of device 0000:00:04.0 to 64
0000:00:04.0: sis190 at ffffc20000004c00 (IRQ: 11), 00:11:2f:e9:42:70
eth0: Enabling Auto-negotiation.
eth0: status = 22000000
eth0: mii 0x1f = 0000.
eth0: mii lpa = 4501.
eth0: Link on 1000 Mbps Full Duplex mode.
eth0: no IPv6 routers present
eth0: status = 0000000c
eth0: status = 00000040
eth0: Rx status = 40040040
eth0: Rx PSize = 01010040
sk_buff[0]->tail = ffff810013381010
eth0: Rx status = c0000000
[...]
eth0: status = 20000040
eth0: dirty_rx=30 cur_rx=30
PSize status addr size PSize status addr size
00:00000000 c0000000 13381010 00000600 00000000 c0000000 13847010 00000600
01:00000000 c0000000 1edcb810 00000600 00000000 c0000000 1b694810 00000600
02:00000000 c0000000 1b697010 00000600 00000000 c0000000 077c4810 00000600
03:00000000 c0000000 07e15010 00000600 00000000 c0000000 06e3e810 00000600
04:00000000 c0000000 1719e810 00000600 00000000 c0000000 1b69b810 00000600
05:00000000 c0000000 1b694010 00000600 00000000 c0000000 07741010 00000600
06:00000000 c0000000 065d8010 00000600 00000000 c0000000 07a84010 00000600
07:010100a6 76040040 13381810 00000600 00000000 c0000000 1f7c1010 00000600
eth0: dirty_tx=36 cur_tx=36
PSize status addr size PSize status addr size
00 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
01 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
02 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
03 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
04 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
05 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
06 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
07 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
eth0: Rx status = 76040040
eth0: Rx PSize = 010100a6
sk_buff[0]->tail = ffff810013381810
eth0: Rx status = c0000000
eth0: status = 0000000c
eth0: status = 000000c0
eth0: dirty_rx=31 cur_rx=31
PSize status addr size PSize status addr size
00:00000000 c0000000 13381010 00000600 00000000 c0000000 13847010 00000600
01:00000000 c0000000 1edcb810 00000600 00000000 c0000000 1b694810 00000600
02:00000000 c0000000 1b697010 00000600 00000000 c0000000 077c4810 00000600
03:00000000 c0000000 07e15010 00000600 00000000 c0000000 06e3e810 00000600
04:00000000 c0000000 1719e810 00000600 00000000 c0000000 1b69b810 00000600
05:00000000 c0000000 1b694010 00000600 00000000 c0000000 07741010 00000600
06:00000000 c0000000 065d8010 00000600 00000000 c0000000 07a84010 00000600
07:00000000 c0000000 13381810 00000600 010100a6 76040040 1f7c1010 00000600
eth0: dirty_tx=37 cur_tx=37
PSize status addr size PSize status addr size
00 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
01 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
02 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
03 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
04 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
05 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
06 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
07 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
eth0: Rx status = 76040040
eth0: Rx PSize = 010100a6
sk_buff[0]->tail = ffff81001f7c1010
eth0: Rx status = c0000000
eth0: status = 0000000c
eth0: status = 0000000c
eth0: status = 0000000c
eth0: status = 2000000c
eth0: status = 2000000c
eth0: status = 2000000c
eth0: status = 2000000c
eth0: status = 2000000c
eth0: status = 2000000c
eth0: status = 2000000c
eth0: status = 2000000c
[...]
No more traces about RxDescRing after that, as
status & (RxQInt) was always 0 in sis190_interrupt().
# ifconfig
eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
inet addr:10.169.21.20 Bcast:10.169.23.255 Mask:255.255.252.0
inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:32 errors:0 dropped:0 overruns:0 frame:0
TX packets:87 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:4833 (4.7 KiB) TX bytes:7364 (7.1 KiB)
Interrupt:11 Base address:0xdead
After that, i made various tries (most of them stupids).
I noticed that whith the default packet size, ping could work
as long as i wanted.
So i removed the test "if (pkt_size < rx_copybreak) {" in sis190_try_rx_copy().
The driver now works "correctly" (ping, ssh, scp) as long as i want,
but probably not in the way you want...
I don't understand how the Rx packets are managed when pkt_size is
greater than rx_copybreak...
I also tried to force 10H, 10F, 100H, 100F autoneg off on the other card.
All modes were working, but obviously something was wrong :
- 10H 0,4Mo/s both directions
- 10F 1,2Mo/s " "
- 100H 5Mo/s " "
- 100F 1,2Mo/s and 0,3Mo/s
For 100F, sis190 reported "100 Mbps Half Duplex" and the other card 100 Full.
Autoneg on gived 100 Full detected and 5Mo/s both directions...
# diff -puN sis190-20050616.c sis190.c
--- sis190-20050616.c 2005-06-17 11:56:46.000000000 +0200
+++ sis190.c 2005-06-17 12:59:08.000000000 +0200
@@ -450,7 +450,6 @@ static inline int sis190_try_rx_copy(str
{
int ret = -1;
- if (pkt_size < rx_copybreak) {
struct sk_buff *skb;
skb = dev_alloc_skb(pkt_size + NET_IP_ALIGN);
@@ -463,7 +462,6 @@ static inline int sis190_try_rx_copy(str
sis190_give_to_asic(desc, rx_buf_sz);
ret = 0;
}
- }
return ret;
}
@@ -637,7 +635,8 @@ static irqreturn_t sis190_interrupt(int
SIS_W32(IntrStatus, status);
- printk(KERN_INFO "%s: status = %08x\n", dev->name, status);
+ if ( status != 0x20000000)
+ printk(KERN_INFO "%s: status = %08x\n", dev->name, status);
if ((status & LinkChange) && netif_running(dev)) {
printk(KERN_INFO "%s: link change\n", dev->name);
@@ -647,8 +646,8 @@ static irqreturn_t sis190_interrupt(int
if ((status & (TxQ0Int | RxQInt)) == 0)
break;
- if (status & (RxQInt))
- sis190_rx_interrupt(dev, tp, ioaddr);
+ if (status & (RxQInt))
+ sis190_rx_interrupt(dev, tp, ioaddr);
if (status & (TxQ0Int)) {
spin_lock(&tp->lock);
@@ -845,7 +844,7 @@ static void sis190_phy_task(void * data)
val = mdio_read(ioaddr, MII_LPA);
printk(KERN_INFO "%s: mii lpa = %04x.\n", dev->name, val);
for (p = reg31; p->ctl; p++) {
- if (val & p->val)
+ if ((val & p->val) == p->val)
break;
}
if (p->ctl)
@@ -1233,31 +1232,11 @@ static void sis190_get_drvinfo(struct ne
struct ethtool_drvinfo *info)
{
struct sis190_private *tp = netdev_priv(dev);
- unsigned int i;
- u32 *u;
strcpy(info->driver, DRV_NAME);
strcpy(info->version, DRV_VERSION);
strcpy(info->bus_info, pci_name(tp->pci_dev));
- printk(KERN_INFO "%s: dirty_rx=%ld cur_rx=%ld\n",
- dev->name, tp->dirty_rx, tp->cur_rx);
- u = (void *) tp->RxDescRing;
- printk(KERN_INFO " PSize status addr size PSize status addr size\n");
- for (i = 0; i < (NUM_RX_DESC / 2); i++) {
- printk(KERN_INFO "%02d:%08x %08x %08x %08x %08x %08x %08x %08x\n",
- i, u[0], u[1], u[2], u[3], u[4], u[5], u[6], u[7]);
- u += 8;
- }
- printk(KERN_INFO "%s: dirty_tx=%ld cur_tx=%ld\n",
- dev->name, tp->dirty_tx, tp->cur_tx);
- u = (void *) tp->TxDescRing;
- printk(KERN_INFO " PSize status addr size PSize status addr size\n");
- for (i = 0; i < (NUM_TX_DESC / 2); i++) {
- printk(KERN_INFO "%02d %08x %08x %08x %08x %08x %08x %08x %08x\n",
- i, u[0], u[1], u[2], u[3], u[4], u[5], u[6], u[7]);
- u += 8;
- }
}
static struct ethtool_ops sis190_ethtool_ops = {
@@ -1311,6 +1290,7 @@ static int __devinit sis190_init_one(str
dev->open = sis190_open;
dev->hard_start_xmit = sis190_start_xmit;
dev->get_stats = sis190_get_stats;
+ SET_ETHTOOL_OPS(dev, &sis190_ethtool_ops);
dev->stop = sis190_close;
dev->tx_timeout = sis190_tx_timeout;
dev->set_multicast_list = sis190_set_rx_mode;
Regards
Pascal
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-14 14:14 sis190 Pascal CHAPPERON
@ 2005-06-14 20:04 ` Francois Romieu
0 siblings, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-06-14 20:04 UTC (permalink / raw)
To: Pascal CHAPPERON; +Cc: Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
Pascal CHAPPERON <pascal.chapperon@wanadoo.fr> :
[20050613-2.6.12-rc-sis190-test.patch]
> I tried it :
> - false mode detection
> - as you expected, ping -s 157 was OK, ping -s 158 failed.
>
> Nice, it begins to work!
Yes.
Notice how the supposedly Rx DMA address ends in your log:
sk_buff[0]->tail = ffff810006a3e012
^
I have tweaked the rx copybreak path to perform a shift from two bytes
before this address and surprisingly enough we get exactly the two
missing bytes. The normal path has not been modified and it is taken
as soon as there is at least 200 bytes of data, i.e. your 186 icmp
payload: it fails as it misses two bytes. Two possible explanations:
1 - I can not find where the two bytes are lost and it is actually a bug
in the driver. So far, you have been quite good at detecting my mistakes.
You know what you have to do :o)
2 - the asic can only DMA to a 4 bytes aligned address.
(actually the asic could also always DMA 2 bytes before the expected address,
whatever the adress, but I'd be happily surprized).
If 2) applies, the driver will need an extra copy to align the IP headers
(or someone will find some secret documentation which explains how to
remove two bytes and fix the issue).
The patch of the day uses a 4 bytes aligned Rx buffer address (at least for
the usual MTU) and copies the Rx data. Can you reproduce the usual testing
and tell if it makes a difference ?
Patch available at:
http://www.fr.zoreil.com/people/francois/misc/20050614-2.6.12-rc-sis190-test.patch
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
@ 2005-06-14 14:14 Pascal CHAPPERON
2005-06-14 20:04 ` sis190 Francois Romieu
0 siblings, 1 reply; 27+ messages in thread
From: Pascal CHAPPERON @ 2005-06-14 14:14 UTC (permalink / raw)
To: Francois Romieu; +Cc: Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
> Can you give a try at:
> http://www.fr.zoreil.com/people/francois/misc/20050613-2.6.12-rc-sis190-test.patch
> dmesg + ifconfig + tcpdump (please add a -e option) will be welcome as usual.
> If the driver starts to behave in an usually better way, please issue
> differently sized ping packets to cover the whole allowed range.
> --
> Ueimor
I tried it :
- false mode detection
- as you expected, ping -s 157 was OK, ping -s 158 failed.
Nice, it begins to work!
BTW, i made a small typo in my diff yesterday :
line 833 : { LPA_100HALF, 0x0901, "100 Mbps Half Duplex" },
must be
line 833 : { LPA_100HALF, 0x0801, "100 Mbps Half Duplex" },
to match the old driver.
Results =>
# cat /var/log/messages
[...]
Jun 14 15:24:02 local kernel: sis190 Gigabit Ethernet driver 1.2 loaded
Jun 14 15:24:02 local kernel: ACPI: PCI Interrupt 0000:00:04.0[A] -> Link [LNKD] -> GSI 11 (level, low) -> IRQ 11
Jun 14 15:24:02 local kernel: 0000:00:04.0: sis190 at ffffc20000004c00 (IRQ: 11), 00:11:2f:e9:42:70
Jun 14 15:24:02 local kernel: eth0: Enabling Auto-negotiation.
Jun 14 15:24:02 local kernel: eth0: status = 63000000
Jun 14 15:24:02 local kernel: eth0: status = 20000000
Jun 14 15:24:03 local last message repeated 116 times
Jun 14 15:24:03 local kernel: eth0: status = 22000000
Jun 14 15:24:03 local kernel: eth0: status = 20000000
Jun 14 15:24:04 local last message repeated 44 times
Jun 14 15:24:04 local network: Bringing up interface eth0: succeeded
Jun 14 15:24:04 local kernel: eth0: status = 20000000
Jun 14 15:24:12 local last message repeated 604 times
Jun 14 15:24:12 local kernel: eth0: mii 0x1f = 0000.
Jun 14 15:24:12 local kernel: eth0: mii lpa = 45e1.
Jun 14 15:24:12 local kernel: eth0: Link on 1000 Mbps Full Duplex mode.
Jun 14 15:24:12 local kernel: eth0: status = 20000000
Jun 14 15:24:43 local last message repeated 2360 times
Jun 14 15:25:13 local last message repeated 2285 times
Jun 14 15:25:13 local kernel: eth0: Promiscuous mode enabled.
[...]
Jun 14 15:26:00 local kernel: eth0: Rx status = 400c0040
Jun 14 15:26:00 local kernel: eth0: Rx PSize = 01010040
Jun 14 15:26:00 local kernel: sk_buff[0]->tail = ffff810007acb812
Jun 14 15:26:00 local kernel: eth0: Rx status = c0000000
Jun 14 15:26:00 local kernel: eth0: status = 0000000c
Jun 14 15:26:00 local kernel: eth0: status = 20000040
Jun 14 15:26:00 local kernel: eth0: Rx status = 640c0040
Jun 14 15:26:00 local kernel: eth0: Rx PSize = 01010066
Jun 14 15:26:00 local kernel: sk_buff[0]->tail = ffff810006a3e012
Jun 14 15:26:00 local kernel: eth0: Rx status = c0000000
Jun 14 15:26:00 local kernel: eth0: status = 20000000
Jun 14 15:26:01 local last message repeated 75 times
Jun 14 15:26:01 local kernel: eth0: status = 2000000c
Jun 14 15:26:01 local kernel: eth0: status = 20000040
Jun 14 15:26:01 local kernel: eth0: Rx status = 640c0040
Jun 14 15:26:01 local kernel: eth0: Rx PSize = 01010066
[...]
Jun 14 15:26:01 local kernel: eth0: Rx status = 640c0040
Jun 14 15:26:01 local kernel: eth0: Rx PSize = 01010066
Jun 14 15:26:01 local kernel: sk_buff[0]->tail = ffff810006a3e812
Jun 14 15:26:01 local kernel: eth0: Rx status = c0000000
Jun 14 15:26:01 local kernel: eth0: status = 20000000
Jun 14 15:26:05 local last message repeated 319 times
Jun 14 15:26:05 local kernel: eth0: status = 20000040
Jun 14 15:26:05 local kernel: eth0: Rx status = 400c0040
Jun 14 15:26:05 local kernel: eth0: Rx PSize = 01010040
Jun 14 15:26:05 local kernel: sk_buff[0]->tail = ffff810007205012
Jun 14 15:26:05 local kernel: eth0: Rx status = c0000000
[...]
# ifconfig
eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
inet addr:10.169.21.20 Bcast:10.169.23.255 Mask:255.255.252.0
inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:6 errors:0 dropped:0 overruns:0 frame:0
TX packets:6 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:512 (512.0 b) TX bytes:476 (476.0 b)
Interrupt:11 Base address:0xdead
# ping -c 2 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 56(84) bytes of data.
64 bytes from 10.169.21.1: icmp_seq=0 ttl=64 time=1.55 ms
64 bytes from 10.169.21.1: icmp_seq=1 ttl=64 time=0.416 ms
--- 10.169.21.1 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1000ms
=> tcpdump -enx
tcpdump: verbose output suppressed, use -v or -vv for full protocol decode
listening on eth0, link-type EN10MB (Ethernet), capture size 96 bytes
15:34:22.083935 00:11:2f:e9:42:70 > Broadcast, ethertype ARP (0x0806), length 42: arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
15:34:22.084201 00:30:4f:06:48:6e > 00:11:2f:e9:42:70, ethertype ARP (0x0806), length 60: arp reply 10.169.21.1 is-at 00:30:4f:06:48:6e
0x0000: 0001 0800 0604 0002 0030 4f06 486e 0aa9 .........0O.Hn..
0x0010: 1501 0011 2fe9 4270 0aa9 1514 0000 0000 ..../.Bp........
0x0020: 0000 0000 0000 0000 0000 0000 0000 ..............
15:34:22.084216 00:11:2f:e9:42:70 > 00:30:4f:06:48:6e, ethertype IPv4 (0x0800), length 98: IP 10.169.21.20 > 10.169.21.1: icmp 64: echo request seq 0
0x0000: 4500 0054 0000 4000 4001 fb42 0aa9 1514 E..T..@.@..B....
0x0010: 0aa9 1501 0800 7dab 1a1b 0000 dedc ae42 ......}........B
0x0020: 0000 0000 1347 0100 0000 0000 1011 1213 .....G..........
0x0030: 1415 1617 1819 1a1b 1c1d 1e1f 2021 2223 .............!"#
0x0040: 2425 2627 2829 2a2b 2c2d 2e2f 3031 3233 $%&'()*+,-./0123
0x0050: 3435 45
15:34:22.084604 00:30:4f:06:48:6e > 00:11:2f:e9:42:70, ethertype IPv4 (0x0800), length 98: IP 10.169.21.1 > 10.169.21.20: icmp 64: echo reply seq 0
0x0000: 4500 0054 c523 0000 4001 761f 0aa9 1501 E..T.#..@.v.....
0x0010: 0aa9 1514 0000 85ab 1a1b 0000 dedc ae42 ...............B
0x0020: 0000 0000 1347 0100 0000 0000 1011 1213 .....G..........
0x0030: 1415 1617 1819 1a1b 1c1d 1e1f 2021 2223 .............!"#
0x0040: 2425 2627 2829 2a2b 2c2d 2e2f 3031 3233 $%&'()*+,-./0123
0x0050: 3435 45
15:34:23.083813 00:11:2f:e9:42:70 > 00:30:4f:06:48:6e, ethertype IPv4 (0x0800), length 98: IP 10.169.21.20 > 10.169.21.1: icmp 64: echo request seq 1
0x0000: 4500 0054 0001 4000 4001 fb41 0aa9 1514 E..T..@.@..A....
0x0010: 0aa9 1501 0800 4baa 1a1b 0001 dfdc ae42 ......K........B
0x0020: 0000 0000 4447 0100 0000 0000 1011 1213 ....DG..........
0x0030: 1415 1617 1819 1a1b 1c1d 1e1f 2021 2223 .............!"#
0x0040: 2425 2627 2829 2a2b 2c2d 2e2f 3031 3233 $%&'()*+,-./0123
0x0050: 3435 45
15:34:23.084199 00:30:4f:06:48:6e > 00:11:2f:e9:42:70, ethertype IPv4 (0x0800), length 98: IP 10.169.21.1 > 10.169.21.20: icmp 64: echo reply seq 1
0x0000: 4500 0054 c524 0000 4001 761e 0aa9 1501 E..T.$..@.v.....
0x0010: 0aa9 1514 0000 53aa 1a1b 0001 dfdc ae42 ......S........B
0x0020: 0000 0000 4447 0100 0000 0000 1011 1213 ....DG..........
0x0030: 1415 1617 1819 1a1b 1c1d 1e1f 2021 2223 .............!"#
0x0040: 2425 2627 2829 2a2b 2c2d 2e2f 3031 3233 $%&'()*+,-./0123
0x0050: 3435 45
15:34:27.084058 00:30:4f:06:48:6e > 00:11:2f:e9:42:70, ethertype ARP (0x0806), length 60: arp who-has 10.169.21.20 tell 10.169.21.1
0x0000: 0001 0800 0604 0001 0030 4f06 486e 0aa9 .........0O.Hn..
0x0010: 1501 0000 0000 0000 0aa9 1514 0000 0000 ................
0x0020: 0000 0000 0000 0000 0000 0000 0000 ..............
15:34:27.084078 00:11:2f:e9:42:70 > 00:30:4f:06:48:6e, ethertype ARP (0x0806), length 42: arp reply 10.169.21.20 is-at 00:11:2f:e9:42:70
0x0000: 0001 0800 0604 0002 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0030 4f06 486e 0aa9 1501 ...0O.Hn....
# ping -c 1 -s 157 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 157(185) bytes of data.
165 bytes from 10.169.21.1: icmp_seq=0 ttl=64 time=0.481 ms
--- 10.169.21.1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
=> tcpdump (local)
15:39:06.194120 00:11:2f:e9:42:70 > 00:30:4f:06:48:6e, ethertype IPv4 (0x0800), length 199: IP 10.169.21.20 > 10.169.21.1: icmp 165: echo request seq 0
0x0000: 4500 00b9 0000 4000 4001 fadd 0aa9 1514 E.....@.@.......
0x0010: 0aa9 1501 0800 1832 231b 0000 fadd ae42 .......2#......B
0x0020: 0000 0000 1ff6 0200 0000 0000 1011 1213 ................
0x0030: 1415 1617 1819 1a1b 1c1d 1e1f 2021 2223 .............!"#
0x0040: 2425 2627 2829 2a2b 2c2d 2e2f 3031 3233 $%&'()*+,-./0123
0x0050: 3435 45
15:39:06.194560 00:30:4f:06:48:6e > 00:11:2f:e9:42:70, ethertype IPv4 (0x0800), length 199: IP 10.169.21.1 > 10.169.21.20: icmp 165: echo reply seq 0
0x0000: 4500 00b9 c52d 0000 4001 75b0 0aa9 1501 E....-..@.u.....
0x0010: 0aa9 1514 0000 2032 231b 0000 fadd ae42 .......2#......B
0x0020: 0000 0000 1ff6 0200 0000 0000 1011 1213 ................
0x0030: 1415 1617 1819 1a1b 1c1d 1e1f 2021 2223 .............!"#
0x0040: 2425 2627 2829 2a2b 2c2d 2e2f 3031 3233 $%&'()*+,-./0123
0x0050: 3435 45
15:39:11.192978 00:11:2f:e9:42:70 > 00:30:4f:06:48:6e, ethertype ARP (0x0806), length 42: arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
15:39:11.193170 00:30:4f:06:48:6e > 00:11:2f:e9:42:70, ethertype ARP (0x0806), length 60: arp reply 10.169.21.1 is-at 00:30:4f:06:48:6e
0x0000: 0001 0800 0604 0002 0030 4f06 486e 0aa9 .........0O.Hn..
0x0010: 1501 0011 2fe9 4270 0aa9 1514 0000 0000 ..../.Bp........
0x0020: 0000 0000 0000 0000 0000 0000 0000 ..............
# ping -c 1 -s 158 10.169.21.1
PING 10.169.21.1 (10.169.21.1) 158(186) bytes of data.
--- 10.169.21.1 ping statistics ---
1 packets transmitted, 0 received, 100% packet loss, time 0ms
=> tcpdump
15:41:29.529515 00:11:2f:e9:42:70 > 00:30:4f:06:48:6e, ethertype IPv4 (0x0800), length 200: IP 10.169.21.20 > 10.169.21.1: icmp 166: echo request seq 0
0x0000: 4500 00ba 0000 4000 4001 fadc 0aa9 1514 E.....@.@.......
0x0010: 0aa9 1501 0800 5c76 261b 0000 89de ae42 ......\v&......B
0x0020: 0000 0000 4314 0800 0000 0000 1011 1213 ....C...........
0x0030: 1415 1617 1819 1a1b 1c1d 1e1f 2021 2223 .............!"#
0x0040: 2425 2627 2829 2a2b 2c2d 2e2f 3031 3233 $%&'()*+,-./0123
0x0050: 3435 45
15:41:29.529940 4f:06:48:6e:08:00 > 2f:e9:42:70:00:30, ethertype Unknown (0x4500), length 200:
0x0000: 00ba c52f 0000 4001 75ad 0aa9 1501 0aa9 .../..@.u.......
0x0010: 1514 0000 6476 261b 0000 89de ae42 0000 ....dv&......B..
0x0020: 0000 4314 0800 0000 0000 1011 1213 1415 ..C.............
0x0030: 1617 1819 1a1b 1c1d 1e1f 2021 2223 2425 ...........!"#$%
0x0040: 2627 2829 2a2b 2c2d 2e2f 3031 3233 3435 &'()*+,-./012345
0x0050: 3637 67
15:41:34.528188 00:11:2f:e9:42:70 > 00:30:4f:06:48:6e, ethertype ARP (0x0806), length 42: arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
15:41:34.528396 00:30:4f:06:48:6e > 00:11:2f:e9:42:70, ethertype ARP (0x0806), length 60: arp reply 10.169.21.1 is-at 00:30:4f:06:48:6e
0x0000: 0001 0800 0604 0002 0030 4f06 486e 0aa9 .........0O.Hn..
0x0010: 1501 0011 2fe9 4270 0aa9 1514 0000 0000 ..../.Bp........
0x0020: 0000 0000 0000 0000 0000 0000 0000 ..............
I could not make tcpdump on the server, as now i have only one monitor (the other is out of order since yesterday evening).
Regards
Pascal
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-13 8:19 sis190 Pascal CHAPPERON
@ 2005-06-13 21:39 ` Francois Romieu
0 siblings, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-06-13 21:39 UTC (permalink / raw)
To: Pascal CHAPPERON; +Cc: Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
Pascal CHAPPERON <pascal.chapperon@wanadoo.fr> :
[...]
> NOTE : here is something strange about base address =>
> dmesg : sis190 at ffffc20000004c00 (IRQ: 11)
> ifconfig : Interrupt:11 Base address:0xbeef
Don't bother: the base address in the struct netdevice is obsolete. I'll
turn it into 0xdead.
[tcpdump output]
> It seems that sis190 driver shifts 4 bytes...
Ok (it looks like a 2 bytes offset though).
> further test about autoneg, probably silly:
> be nice, as i know nothing to network drivers dev.
> i do not understand what is LPA_SLCT...
Ahem. It was not a great idea from me to convert from 31 to LPA_SLCT
as LPA_SLCT is intended to be a bitmask, not a register shift.
> # diff -puN sis190-20050611a.c sis190.c
> --- sis190-20050611a.c 2005-06-13 08:54:56.000000000 +0200
> +++ sis190.c 2005-06-13 09:41:29.000000000 +0200
[...]
> @@ -823,18 +823,17 @@ static void sis190_phy_task(void * data)
> u16 ctl;
> const char *msg;
> } reg31[] = {
> - { _1000bpsF, 0x1c01, "1000 bps Full Duplex" },
> - { _1000bpsH, 0x0c01, "1000 bps Half Duplex" },
> - { _100bpsF, 0x1801, "100 bps Full Duplex" },
> - { _100bpsH, 0x0801, "100 bps Half Duplex" },
> - { _10bpsF, 0x1401, "10 bps Full Duplex" },
> - { _10bpsH, 0x0401, "10 bps Half Duplex" },
> + { LPA_1000XFULL | LPA_SLCT, 0x1c01, "1000 bps Full Duplex" },
> + { LPA_1000XHALF | LPA_SLCT, 0x0c01, "1000 bps Half Duplex" },
> + { LPA_100FULL, 0x1801, "100 bps Full Duplex" },
> + { LPA_100HALF, 0x0901, "100 bps Half Duplex" },
> + { LPA_10FULL, 0x1401, "10 bps Full Duplex" },
> + { LPA_10HALF, 0x0401, "10 bps Half Duplex" },
> { 0, 0x0000, "unknown" }
> }, *p;
> - val = mdio_read(ioaddr, LPA_SLCT) & 0x1c; // bit 4:2
> -
> + val = mdio_read(ioaddr, MII_LPA);
> for (p = reg31; p->ctl; p++) {
> - if (val == p->val)
> + if ((val & p->val) == p->val)
> break;
> }
> if (p->ctl)
[and it works]
Cool. Ok, I take that and I'll sprinkle a few printks here and there.
Can you give a try at:
http://www.fr.zoreil.com/people/francois/misc/20050613-2.6.12-rc-sis190-test.patch
dmesg + ifconfig + tcpdump (please add a -e option) will be welcome as usual.
If the driver starts to behave in an usually better way, please issue
differently sized ping packets to cover the whole allowed range.
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
@ 2005-06-13 8:19 Pascal CHAPPERON
2005-06-13 21:39 ` sis190 Francois Romieu
0 siblings, 1 reply; 27+ messages in thread
From: Pascal CHAPPERON @ 2005-06-13 8:19 UTC (permalink / raw)
To: Francois Romieu; +Cc: Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
> Message du 11/06/05 12:58
> De : "Francois Romieu" <romieu@fr.zoreil.com>
> Can you reproduce the tests (dhcp/no dhcp) with the patch linked below and
> add a tcpdump -x output taken at the server as an addition to the usual
> information ?
>
> http://www.fr.zoreil.com/people/francois/misc/20050611a-2.6.12-rc-sis190-test.patch
>
> If you are in a hurry and have any output, I'll look at it today (~18h).
>
> Thanks.
>
> --
> Ueimor
>
>
No, i am not in hurry, and many thanks for working on this driver.
The results :
# cat /var/log/messages
Jun 13 09:04:27 local kernel: sis190 Gigabit Ethernet driver 1.2 loaded
Jun 13 09:04:27 local kernel: ACPI: PCI Interrupt Link [LNKD] enabled at IRQ 11
Jun 13 09:04:27 local kernel: ACPI: PCI Interrupt 0000:00:04.0[A] -> Link [LNKD] -> GSI 11 (level, low) -> IRQ 11
Jun 13 09:04:27 local kernel: 0000:00:04.0: sis190 at ffffc20000004c00 (IRQ: 11), 00:11:2f:e9:42:70
Jun 13 09:04:27 local kernel: eth0: Enabling Auto-negotiation.
Jun 13 09:04:27 local kernel: eth0: status = 20000000
Jun 13 09:04:29 local last message repeated 155 times
Jun 13 09:04:29 local kernel: eth0: status = 20010000
Jun 13 09:04:29 local kernel: eth0: link change
Jun 13 09:04:29 local kernel: eth0: Link on unknown mode.
Jun 13 09:04:29 local kernel: eth0: status = 20000000
Jun 13 09:04:29 local last message repeated 4 times
Jun 13 09:04:29 local network: Bringing up interface eth0: succeeded
Jun 13 09:04:29 local kernel: eth0: status = 20000000
Jun 13 09:04:31 local last message repeated 147 times
Jun 13 09:04:31 local kernel: eth0: status = 2000000c
Jun 13 09:04:31 local kernel: eth0: status = 20000000
...
Jun 13 09:05:02 local kernel: eth0: Rx status = 40040040
Jun 13 09:05:02 local kernel: eth0: Rx PSize = 01010040
Jun 13 09:05:02 local kernel: eth0: Rx status = c0000000
Jun 13 09:05:03 local kernel: eth0: Rx status = 40040040
Jun 13 09:05:03 local kernel: eth0: Rx PSize = 01010040
Jun 13 09:05:03 local kernel: eth0: Rx status = c0000000
Jun 13 09:05:04 local kernel: eth0: Rx status = 40040040
Jun 13 09:05:04 local kernel: eth0: Rx PSize = 01010040
Jun 13 09:05:04 local kernel: eth0: Rx status = c0000000
Jun 13 09:05:05 local kernel: eth0: Rx status = 40040040
Jun 13 09:05:05 local kernel: eth0: Rx PSize = 01010040
Jun 13 09:05:05 local kernel: eth0: Rx status = c0000000
Jun 13 09:05:06 local kernel: eth0: Rx status = 40040040
Jun 13 09:05:06 local kernel: eth0: Rx PSize = 01010040
Jun 13 09:05:06 local kernel: eth0: Rx status = c0000000
Jun 13 09:05:07 local kernel: eth0: Rx status = 40040040
Jun 13 09:05:07 local kernel: eth0: Rx PSize = 01010040
Jun 13 09:05:07 local kernel: eth0: Rx status = c0000000
...
# ifconfig
eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
inet addr:10.169.21.20 Bcast:10.169.23.255 Mask:255.255.252.0
inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:141 errors:0 dropped:0 overruns:0 frame:0
TX packets:144 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:8460 (8.2 KiB) TX bytes:6104 (5.9 KiB)
Interrupt:11 Base address:0xbeef
NOTE : here is something strange about base address =>
dmesg : sis190 at ffffc20000004c00 (IRQ: 11)
ifconfig : Interrupt:11 Base address:0xbeef
# local tcpdump : ping server 10.169.21.1 from local 10.169.21.20
09:09:41.798748 arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
09:09:41.798920 4f:06:48:6e:08:06 null > 2f:e9:42:70:00:30 sap 08 I (s=3,r=2,C) len=42
0x0000: 0800 0604 0002 0030 4f06 486e 0aa9 1501 .......0O.Hn....
0x0010: 0011 2fe9 4270 0aa9 1514 0000 0000 0000 ../.Bp..........
0x0020: 0000 0000 0000 0000 0000 0000 0c15 ..............
09:09:42.798592 arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 ............
09:09:42.798767 4f:06:48:6e:08:06 null > 2f:e9:42:70:00:30 sap 08 I (s=3,r=2,C) len=42
0x0000: 0800 0604 0002 0030 4f06 486e 0aa9 1501 .......0O.Hn....
0x0010: 0011 2fe9 4270 0aa9 1514 0000 0000 0000 ../.Bp..........
0x0020: 0000 0000 0000 0000 0000 0000 0c15 ..............
...
# server tcpdump : ping server 10.169.21.1 from local 10.169.21.20
09:27:40.749713 arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 0000 0000 ................
0x0020: 0000 0000 0000 0000 0000 0000 0000 ..............
09:27:40.749797 arp reply 10.169.21.1 is-at 00:30:4f:06:48:6e
0x0000: 0001 0800 0604 0002 0030 4f06 486e 0aa9 .........0O.Hn..
0x0010: 1501 0011 2fe9 4270 0aa9 1514 ..../.Bp....
09:27:41.749522 arp who-has 10.169.21.1 tell 10.169.21.20
0x0000: 0001 0800 0604 0001 0011 2fe9 4270 0aa9 ........../.Bp..
0x0010: 1514 0000 0000 0000 0aa9 1501 0000 0000 ................
0x0020: 0000 0000 0000 0000 0000 0000 0000 ..............
09:27:41.749605 arp reply 10.169.21.1 is-at 00:30:4f:06:48:6e
0x0000: 0001 0800 0604 0002 0030 4f06 486e 0aa9 .........0O.Hn..
0x0010: 1501 0011 2fe9 4270 0aa9 1514 ..../.Bp....
It seems that sis190 driver shifts 4 bytes...
further test about autoneg, probably silly:
be nice, as i know nothing to network drivers dev.
i do not understand what is LPA_SLCT...
modification :
# diff -puN sis190-20050611a.c sis190.c
--- sis190-20050611a.c 2005-06-13 08:54:56.000000000 +0200
+++ sis190.c 2005-06-13 09:41:29.000000000 +0200
@@ -630,7 +630,7 @@ static irqreturn_t sis190_interrupt(int
SIS_W32(IntrStatus, status);
- printk(KERN_INFO "%s: status = %08x\n", dev->name, status);
+ // printk(KERN_INFO "%s: status = %08x\n", dev->name, status);
if ((status & LinkChange) && netif_running(dev)) {
printk(KERN_INFO "%s: link change\n", dev->name);
@@ -823,18 +823,17 @@ static void sis190_phy_task(void * data)
u16 ctl;
const char *msg;
} reg31[] = {
- { _1000bpsF, 0x1c01, "1000 bps Full Duplex" },
- { _1000bpsH, 0x0c01, "1000 bps Half Duplex" },
- { _100bpsF, 0x1801, "100 bps Full Duplex" },
- { _100bpsH, 0x0801, "100 bps Half Duplex" },
- { _10bpsF, 0x1401, "10 bps Full Duplex" },
- { _10bpsH, 0x0401, "10 bps Half Duplex" },
+ { LPA_1000XFULL | LPA_SLCT, 0x1c01, "1000 bps Full Duplex" },
+ { LPA_1000XHALF | LPA_SLCT, 0x0c01, "1000 bps Half Duplex" },
+ { LPA_100FULL, 0x1801, "100 bps Full Duplex" },
+ { LPA_100HALF, 0x0901, "100 bps Half Duplex" },
+ { LPA_10FULL, 0x1401, "10 bps Full Duplex" },
+ { LPA_10HALF, 0x0401, "10 bps Half Duplex" },
{ 0, 0x0000, "unknown" }
}, *p;
- val = mdio_read(ioaddr, LPA_SLCT) & 0x1c; // bit 4:2
-
+ val = mdio_read(ioaddr, MII_LPA);
for (p = reg31; p->ctl; p++) {
- if (val == p->val)
+ if ((val & p->val) == p->val)
break;
}
if (p->ctl)
# dmesg
...
[ remote card forced in 10 half autoneg off ]
...
sis190 Gigabit Ethernet driver 1.2 loaded
ACPI: PCI Interrupt 0000:00:04.0[A] -> Link [LNKD] -> GSI 11 (level, low) ->
IRQ 11
PCI: Setting latency timer of device 0000:00:04.0 to 64
0000:00:04.0: sis190 at ffffc20000004c00 (IRQ: 11), 00:11:2f:e9:42:70
eth0: Enabling Auto-negotiation.
eth0: Link on 10 bps Half Duplex mode.
eth0: no IPv6 routers present
...
[ remote card in 10 full autoneg off ]
[ I must restart the network to have (false) mode detection ]
...
eth0: Link on 10 bps Half Duplex mode.
eth0: Link on 10 bps Half Duplex mode.
...
[ remote card in 100 full autoneg on ]
[ no network restart ]
...
eth0: no IPv6 routers present
eth0: link change
eth0: PHY reset until link up
eth0: link change
eth0: Link on 100 bps Full Duplex mode.
eth0: Link on 100 bps Full Duplex mode.
...
Regards
Pascal
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-11 9:39 sis190 Pascal CHAPPERON
@ 2005-06-11 10:56 ` Francois Romieu
0 siblings, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-06-11 10:56 UTC (permalink / raw)
To: Pascal CHAPPERON; +Cc: Andrew Hutchings, linux-kernel, vinay kumar, jgarzik
Pascal CHAPPERON <pascal.chapperon@wanadoo.fr> :
[...]
> Sorry, but it does not compile correctly if you define CONFIG_SIS190_NO_DELAY.
The safe choice is to not define it. I did not make it clear enough.
[...]
> I compared sis190_rx_interrupt() in old and new driver, and i tried :
> diff -puN /usr/src/linux/drivers/net/sis190.c sis190.c
> --- /usr/src/linux/drivers/net/sis190.c 2005-06-11 09:16:41.000000000 +0200
> +++ sis190.c 2005-06-11 10:20:01.000000000 +0200
> @@ -478,7 +478,7 @@ static int sis190_rx_interrupt(struct ne
> rmb();
> status = le32_to_cpu(desc->PSize);
>
> - if (status & OWNbit)
> + if (desc->status & OWNbit)
> break;
>
> if (status & RxCRC) {
Good catch.
[...]
> I also tried without dhcp :
> # ifconfig
> eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
> inet addr:10.169.21.20 Bcast:10.169.23.255 Mask:255.255.252.0
> inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
> UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
> RX packets:59 errors:0 dropped:0 overruns:0 frame:0
> TX packets:43 errors:0 dropped:0 overruns:0 carrier:0
> collisions:0 txqueuelen:1000
> RX bytes:4148 (4.0 KiB) TX bytes:1806 (1.7 KiB)
> Interrupt:10 Base address:0xbeef
>
> ping failed both sides, though RX and TX counters were incremented.
Can you reproduce the tests (dhcp/no dhcp) with the patch linked below and
add a tcpdump -x output taken at the server as an addition to the usual
information ?
http://www.fr.zoreil.com/people/francois/misc/20050611a-2.6.12-rc-sis190-test.patch
If you are in a hurry and have any output, I'll look at it today (~18h).
Thanks.
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
@ 2005-06-11 9:39 Pascal CHAPPERON
2005-06-11 10:56 ` sis190 Francois Romieu
0 siblings, 1 reply; 27+ messages in thread
From: Pascal CHAPPERON @ 2005-06-11 9:39 UTC (permalink / raw)
To: Francois Romieu, Andrew Hutchings; +Cc: linux-kernel, vinay kumar, jgarzik
> Message du 11/06/05 01:46
> De : "Francois Romieu" <romieu@fr.zoreil.com>
>
> Andrew Hutchings <info@a-wing.co.uk> :
> [...]
> > Something went wrong on build. Getting 'syntax error before '}' token'
> > on every line there is _msleep(1);
>
> I have checked it again and the patch applies and compiles correctly
> against 2.6.12-rc6. So does the updated patch of the day:
>
> http://www.fr.zoreil.com/people/francois/misc/20050611-2.6.12-rc-sis190-test.patch
Sorry, but it does not compile correctly if you define CONFIG_SIS190_NO_DELAY.
# diff -puN /usr/src/linux/drivers/net/sis190.c sis190.c
--- /usr/src/linux/drivers/net/sis190.c 2005-06-11 09:16:41.000000000 +0200
+++ sis190.c 2005-06-11 10:20:01.000000000 +0200
@@ -43,8 +43,8 @@
#endif
#ifdef CONFIG_SIS190_NO_DELAY
-#define s_mdelay(d) do { (d) } while (0)
-#define s_msleep(d) do { (d) } while (0)
+#define s_mdelay(d) do { } while (0)
+#define s_msleep(d) do { } while (0)
#else
#define s_mdelay(d) mdelay(d)
#define s_msleep(d) msleep(d)
So it works.
>
> No need to use SIS190_NO_DELAY so far. The media negotiation process has
> been changed. It is now allowed to take longer to complete (it should help).
>
> dmesg and ifconfig output will be welcome.
>
> --
> Ueimor
>
>
It still do not work :
#dmesg
...
sis190 Gigabit Ethernet driver 1.2 loaded
ACPI: PCI Interrupt 0000:00:04.0[A] -> Link [LNKD] -> GSI 10 (level, low) -> IRQ 10
PCI: Setting latency timer of device 0000:00:04.0 to 64
0000:00:04.0: sis190 at ffffc20000026c00 (IRQ: 10), 00:11:2f:e9:42:70
eth0: Enabling Auto-negotiation.
eth0: Link on unknown mode.
eth0: no IPv6 routers present
eth0: status = 20000008
eth0: status = 00000004
eth0: status = 20000008
eth0: status = 00000004
eth0: pad error. status = 00000000
eth0: pad error. status = 00000000
eth0: pad error. status = 00000000
eth0: pad error. status = 00000000
...
#ifconfig
eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:8 errors:248 dropped:0 overruns:0 frame:248
TX packets:8 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:762 (762.0 b) TX bytes:1404 (1.3 KiB)
Interrupt:10 Base address:0xbeef
I compared sis190_rx_interrupt() in old and new driver, and i tried :
diff -puN /usr/src/linux/drivers/net/sis190.c sis190.c
--- /usr/src/linux/drivers/net/sis190.c 2005-06-11 09:16:41.000000000 +0200
+++ sis190.c 2005-06-11 10:20:01.000000000 +0200
@@ -478,7 +478,7 @@ static int sis190_rx_interrupt(struct ne
rmb();
status = le32_to_cpu(desc->PSize);
- if (status & OWNbit)
+ if (desc->status & OWNbit)
break;
if (status & RxCRC) {
new test :
# dmesg
...
sis190 Gigabit Ethernet driver 1.2 loaded
ACPI: PCI Interrupt 0000:00:04.0[A] -> Link [LNKD] -> GSI 10 (level, low) -> IRQ 10
PCI: Setting latency timer of device 0000:00:04.0 to 64
0000:00:04.0: sis190 at ffffc20000026c00 (IRQ: 10), 00:11:2f:e9:42:70
eth0: Enabling Auto-negotiation.
eth0: Link on unknown mode.
eth0: no IPv6 routers present
eth0: status = 22000008
eth0: status = 00000004
eth0: status = 20000008
eth0: status = 00000004
eth0: status = 20000040
eth0: status = 20000040
eth0: status = 20000040
eth0: status = 20000040
eth0: status = 20000008
eth0: status = 00000004
...
#ifconfig
eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:6 errors:0 dropped:0 overruns:0 frame:0
TX packets:3 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:1206 (1.1 KiB) TX bytes:1026 (1.0 KiB)
Interrupt:10 Base address:0xbeef
As you can see, no more RX errors, but the network script failed to establish the link.
On the other box (dhcp server) :
#dmesg
...
eth2: link down
eth2: link up, 100Mbps, full-duplex, lpa 0x41E0
DHCPREQUEST for 10.169.21.20 from 00:11:2f:e9:42:70 via eth2: unknown lease 10.169.21.20.
DHCPDISCOVER from 00:11:2f:e9:42:70 via eth2
DHCPOFFER on 10.169.21.47 to 00:11:2f:e9:42:70 via eth2
DHCPDISCOVER from 00:11:2f:e9:42:70 via eth2
DHCPOFFER on 10.169.21.47 to 00:11:2f:e9:42:70 via eth2
DHCPDISCOVER from 00:11:2f:e9:42:70 via eth2
DHCPOFFER on 10.169.21.47 to 00:11:2f:e9:42:70 via eth2
...
I also tried without dhcp :
# ifconfig
eth0 Link encap:Ethernet HWaddr 00:11:2F:E9:42:70
inet addr:10.169.21.20 Bcast:10.169.23.255 Mask:255.255.252.0
inet6 addr: fe80::211:2fff:fee9:4270/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:59 errors:0 dropped:0 overruns:0 frame:0
TX packets:43 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:4148 (4.0 KiB) TX bytes:1806 (1.7 KiB)
Interrupt:10 Base address:0xbeef
ping failed both sides, though RX and TX counters were incremented.
Regards
Pascal
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-10 13:55 ` sis190 Andrew Hutchings
@ 2005-06-10 23:41 ` Francois Romieu
0 siblings, 0 replies; 27+ messages in thread
From: Francois Romieu @ 2005-06-10 23:41 UTC (permalink / raw)
To: Andrew Hutchings; +Cc: linux-kernel, vinay kumar, jgarzik, pascal.chapperon
Andrew Hutchings <info@a-wing.co.uk> :
[...]
> Something went wrong on build. Getting 'syntax error before '}' token'
> on every line there is _msleep(1);
I have checked it again and the patch applies and compiles correctly
against 2.6.12-rc6. So does the updated patch of the day:
http://www.fr.zoreil.com/people/francois/misc/20050611-2.6.12-rc-sis190-test.patch
No need to use SIS190_NO_DELAY so far. The media negotiation process has
been changed. It is now allowed to take longer to complete (it should help).
dmesg and ifconfig output will be welcome.
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-09 21:18 ` sis190 Francois Romieu
@ 2005-06-10 13:55 ` Andrew Hutchings
2005-06-10 23:41 ` sis190 Francois Romieu
0 siblings, 1 reply; 27+ messages in thread
From: Andrew Hutchings @ 2005-06-10 13:55 UTC (permalink / raw)
To: Francois Romieu; +Cc: linux-kernel, vinay kumar, jgarzik
Francois Romieu wrote:
> Andrew Hutchings <info@a-wing.co.uk> :
> [...]
>
>>Tried it, it didn't detect the sis190 in this board so I changed the
>>PCI_ID lines to:
>>static struct pci_device_id sis190_pci_tbl[] __devinitdata = {
>> { 0x1039, 0x0190, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
>> { 0,},
>>};
>
>
> /me scratches head
>
> The figures look the same. I must be tired.
>
I thought so, but for some reason it makes a difference.
>
>>This then detected it but caused a soft lockup on modprobe with a dump
>>which I have attached here. I have also attched lspci -vvv and -xxx for
>>you.
>
>
> Right, there was a bug. I am not sure the fix will really fix though.
>
> See the patch of the day:
>
> http://www.fr.zoreil.com/people/francois/misc/20050610-2.6.12-rc-sis190-test.patch
>
> Please add a dmesg as well if something goes wrong.
>
Something went wrong on build. Getting 'syntax error before '}' token'
on every line there is _msleep(1);
Regards
Andrew
--
Andrew Hutchings (A-Wing)
Linux Guru - Netserve Consultants Ltd. - http://www.domaincity.co.uk/
Admin - North Wales Linux User Group - http://www.nwlug.org.uk/
BOFH excuse 311: transient bus protocol violation
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-09 12:02 ` sis190 Andrew Hutchings
@ 2005-06-09 21:18 ` Francois Romieu
2005-06-10 13:55 ` sis190 Andrew Hutchings
0 siblings, 1 reply; 27+ messages in thread
From: Francois Romieu @ 2005-06-09 21:18 UTC (permalink / raw)
To: Andrew Hutchings; +Cc: linux-kernel, vinay kumar, jgarzik
Andrew Hutchings <info@a-wing.co.uk> :
[...]
> Tried it, it didn't detect the sis190 in this board so I changed the
> PCI_ID lines to:
> static struct pci_device_id sis190_pci_tbl[] __devinitdata = {
> { 0x1039, 0x0190, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
> { 0,},
> };
/me scratches head
The figures look the same. I must be tired.
> This then detected it but caused a soft lockup on modprobe with a dump
> which I have attached here. I have also attched lspci -vvv and -xxx for
> you.
Right, there was a bug. I am not sure the fix will really fix though.
See the patch of the day:
http://www.fr.zoreil.com/people/francois/misc/20050610-2.6.12-rc-sis190-test.patch
Please add a dmesg as well if something goes wrong.
> FYI, I know the general spec for a sis190 is 1000MBit but the one on
> this mobo is just a 10/100MBit
The driver enables nearly everything via the mii. With some luck it will
be enough to postpone the link management revamp until at least one (1)
packet has proceeded through the driver.
Thanks for your testing.
--
Ueimor
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-08 22:51 ` sis190 (was: Re: sis5513.c patch) Francois Romieu
2005-06-09 4:54 ` sis190 Andrew Hutchings
@ 2005-06-09 12:02 ` Andrew Hutchings
2005-06-09 21:18 ` sis190 Francois Romieu
1 sibling, 1 reply; 27+ messages in thread
From: Andrew Hutchings @ 2005-06-09 12:02 UTC (permalink / raw)
To: Francois Romieu; +Cc: linux-kernel, vinay kumar, jgarzik
[-- Attachment #1: Type: text/plain, Size: 969 bytes --]
Francois Romieu wrote:
> Patch of the day:
>
> http://www.fr.zoreil.com/people/francois/misc/20050609-2.6.12-rc-sis190-test.patch
>
> Apply against current 2.6.12-rc12
>
> I'll be surprized if it works. I'll appreciate to know when and how it
> breaks.
>
> --
> Ueimor
>
Tried it, it didn't detect the sis190 in this board so I changed the
PCI_ID lines to:
static struct pci_device_id sis190_pci_tbl[] __devinitdata = {
{ 0x1039, 0x0190, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 },
{ 0,},
};
This then detected it but caused a soft lockup on modprobe with a dump
which I have attached here. I have also attched lspci -vvv and -xxx for
you.
FYI, I know the general spec for a sis190 is 1000MBit but the one on
this mobo is just a 10/100MBit
Regards
Andrew
--
Andrew Hutchings (A-Wing)
Linux Guru - Netserve Consultants Ltd. - http://www.domaincity.co.uk/
Admin - North Wales Linux User Group - http://www.nwlug.org.uk/
BOFH excuse 330: quantum decoherence
[-- Attachment #2: error.txt --]
[-- Type: text/plain, Size: 2980 bytes --]
Jun 9 19:24:14 localhost dhclient: DHCPDISCOVER on eth1 to 255.255.255.255 port 67 interval 6
Jun 9 19:24:14 localhost kernel: BUG: soft lockup detected on CPU#0!
Jun 9 19:24:14 localhost kernel:
Jun 9 19:24:14 localhost kernel: Modules linked in: sis190 ipv6 parport_pc lp parport autofs4 sunrpc video button battery ac ohci_hcd ehci_hcd sundance mii$Jun 9 19:24:14 localhost kernel: Pid: 3774, comm: modprobe Not tainted 2.6.12-rc6-mm1sis
Jun 9 19:24:14 localhost kernel: RIP: 0010:[<ffffffff80232828>] <ffffffff80232828>{__delay+8}
Jun 9 19:24:14 localhost kernel: RSP: 0018:ffff81000cb85b40 EFLAGS: 00000283
Jun 9 19:24:14 localhost kernel: RAX: 00000000f4359f94 RBX: ffffc200000a6c00 RCX: 00000000f4303df0
Jun 9 19:24:14 localhost kernel: RDX: 00000000000001c2 RSI: 0000000000000850 RDI: 00000000001e70f8
Jun 9 19:24:14 localhost kernel: RBP: ffffc200000a6c00 R08: ffff81000cb84000 R09: 0000000000000000
Jun 9 19:24:14 localhost kernel: R10: 0000000000014859 R11: ffffffff80339660 R12: ffff810016e70000
Jun 9 19:24:14 localhost kernel: R13: ffff810016e70420 R14: ffff81001db76000 R15: 0000000000000029
Jun 9 19:24:14 localhost kernel: FS: 00002aaaaaab3b00(0000) GS:ffffffff8055d840(0000) knlGS:0000000000000000
Jun 9 19:24:14 localhost kernel: CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
Jun 9 19:24:14 localhost dhclient: receive_packet failed on eth1: Network is down
Jun 9 19:24:14 localhost kernel: CR2: 0000003d2122d064 CR3: 000000000d2d4000 CR4: 00000000000006e0
Jun 9 19:24:14 localhost kernel:
Jun 9 19:24:14 localhost kernel: Call Trace:<ffffffff880c9137>{:sis190:mdio_read+23} <ffffffff880cac9d>{:sis190:sis190_init_one+1341}
Jun 9 19:24:14 localhost net.agent[3916]: remove event not handled
Jun 9 19:24:14 localhost net.agent[3925]: remove event not handled
Jun 9 19:24:14 localhost kernel: <ffffffff8023c256>{pci_device_probe+134} <ffffffff8023be95>{pci_bus_match+53}
Jun 9 19:24:15 localhost kernel: <ffffffff802b2d6f>{driver_probe_device+79} <ffffffff802b2ed4>{__driver_attach+84}
Jun 9 19:24:15 localhost kernel: <ffffffff802b2e80>{__driver_attach+0} <ffffffff802b2526>{bus_for_each_dev+70}
Jun 9 19:24:15 localhost kernel: <ffffffff802b2898>{bus_add_driver+136} <ffffffff8023bc20>{pci_register_driver+160}
Jun 9 19:24:15 localhost kernel: <ffffffff80161248>{sys_init_module+6760} <ffffffff801706e1>{generic_file_aio_read+49}
Jun 9 19:24:15 localhost kernel: <ffffffff88145000>{:sis190:sis190_init_module+0} <ffffffff80159590>{autoremove_wake_function+0}
Jun 9 19:24:15 localhost kernel: <ffffffff80199b46>{vfs_read+230} <ffffffff80199ed3>{sys_read+83}
Jun 9 19:24:15 localhost kernel: <ffffffff8010f1e6>{system_call+126}
Jun 9 19:24:15 localhost kernel: sis190: probe of 0000:00:04.0 failed with error -11
Jun 9 19:24:19 localhost dhclient: DHCPDISCOVER on eth1 to 255.255.255.255 port 67 interval 7
Jun 9 19:24:19 localhost dhclient: send_packet: No such device
[-- Attachment #3: out1.txt --]
[-- Type: text/plain, Size: 16524 bytes --]
00:00.0 Host bridge: Silicon Integrated Systems [SiS] 760/M760 Host (rev 03)
00: 39 10 60 07 07 00 10 22 03 00 00 06 00 20 00 00
10: 00 00 00 e0 00 00 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 43 10 59 81
30: 00 00 00 00 a0 00 00 00 00 00 00 00 00 00 00 00
40: 16 00 88 97 00 ff 00 a0 00 10 00 00 51 00 06 00
50: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
70: 00 80 00 00 00 02 00 00 00 00 00 00 00 00 01 08
80: 00 00 00 00 00 00 14 c8 00 00 00 10 00 02 00 1e
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 02 d0 30 00 0b 4e 00 1f 00 02 00 00 00 00 00 00
b0: 00 00 00 00 30 0f 01 00 00 00 00 00 00 00 00 00
c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 08 f0 20 01 60 00 11 10 d0 00 77 77 22 05 35 00
e0: 02 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
f0: 08 00 00 80 44 01 99 f8 00 00 00 00 a8 a8 66 00
00:01.0 PCI bridge: Silicon Integrated Systems [SiS] SG86C202
00: 39 10 02 00 07 01 20 02 00 00 04 06 00 40 01 00
10: 00 00 00 00 00 00 00 00 00 01 01 40 c0 c0 20 22
20: a0 fe a0 fe 90 ee 80 fe 00 00 00 00 00 00 00 00
30: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 0a 00
40: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
50: 02 40 00 00 09 00 80 00 0c 00 00 00 00 00 00 00
60: b0 02 60 60 aa 10 00 00 23 23 18 15 00 00 08 00
70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 08 18 00 02 88 45 28 00 00 00 00 00 40 00 00
d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 15 18 15 18
00:02.0 ISA bridge: Silicon Integrated Systems [SiS] SiS965 [MuTIOL Media IO] (rev 47)
00: 39 10 65 09 0f 00 00 02 47 00 01 06 00 00 80 00
10: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
30: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
40: 91 85 8b 80 85 00 3d dd 10 00 00 00 11 20 04 03
50: 11 28 02 01 60 0b 20 0b a9 04 12 00 0b e9 00 00
60: 8b 83 85 8a ff c1 0c 12 09 80 00 00 97 00 04 14
70: 00 00 ff ff 00 08 03 0c 20 00 00 88 03 00 00 40
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 1f 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 f0 e0 01 00 00 00 00 00 88 00 08 00 00 00 45
d0: 02 00 00 00 44 62 32 00 85 00 04 7b aa aa aa aa
e0: 40 00 00 f8 42 00 44 00 00 00 00 00 00 00 00 00
f0: 0a 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00:02.5 IDE interface: Silicon Integrated Systems [SiS] 5513 [IDE] (rev 01)
00: 39 10 13 55 05 00 10 02 01 80 01 01 00 80 00 00
10: 01 00 00 00 01 00 00 00 01 00 00 00 01 00 00 00
20: a1 ff 00 00 00 00 00 00 00 00 00 00 43 10 39 81
30: 00 00 00 00 58 00 00 00 00 00 00 00 00 00 00 00
40: 00 00 00 00 00 00 00 00 20 00 06 00 00 00 00 00
50: a2 21 a3 a1 2a 96 80 d0 01 00 02 80 00 00 00 00
60: fb aa fb aa 00 00 00 00 00 80 00 00 00 00 00 50
70: b0 66 20 1e 1e 32 09 05 b0 66 20 1e b0 66 20 1e
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00:03.0 USB Controller: Silicon Integrated Systems [SiS] USB 1.0 Controller (rev 0f)
00: 39 10 01 70 17 01 80 02 0f 10 03 0c 00 40 80 00
10: 00 40 bf fe 00 00 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 43 10 39 81
30: 00 00 00 00 00 00 00 00 00 00 00 00 0b 01 00 50
40: 00 00 00 00 5c ae 01 00 3f 02 00 00 00 00 00 00
50: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 00 00 00 00 00 00 00 00 00 00 00 00 01 00 c2 c9
e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00:03.1 USB Controller: Silicon Integrated Systems [SiS] USB 1.0 Controller (rev 0f)
00: 39 10 01 70 17 01 80 02 0f 10 03 0c 00 40 00 00
10: 00 50 bf fe 00 00 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 43 10 39 81
30: 00 00 00 00 00 00 00 00 00 00 00 00 03 02 00 50
40: 00 00 00 00 5c ae 01 00 3f 02 00 00 00 00 00 00
50: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 00 00 00 00 00 00 00 00 00 00 00 00 01 00 c2 c9
e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00:03.2 USB Controller: Silicon Integrated Systems [SiS] USB 1.0 Controller (rev 0f)
00: 39 10 01 70 17 01 80 02 0f 10 03 0c 00 40 00 00
10: 00 60 bf fe 00 00 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 43 10 39 81
30: 00 00 00 00 00 00 00 00 00 00 00 00 05 03 00 50
40: 00 00 00 00 5c ae 01 00 3f 02 00 00 00 00 00 00
50: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 00 00 00 00 00 00 00 00 00 00 00 00 01 00 c2 c9
e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00:03.3 USB Controller: Silicon Integrated Systems [SiS] USB 2.0 Controller
00: 39 10 02 70 06 01 90 02 00 20 03 0c 00 40 00 00
10: 00 70 bf fe 00 00 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 43 10 39 81
30: 00 00 00 00 50 00 00 00 00 00 00 00 0a 04 00 50
40: 00 00 00 08 04 00 00 00 00 00 00 00 00 00 00 00
50: 01 00 c2 c9 00 00 00 00 0a 00 00 21 00 00 00 00
60: 20 20 ff 01 00 00 00 00 00 00 00 00 00 00 00 00
70: 01 00 00 01 00 00 08 80 00 00 cf 3f 00 00 00 00
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00:04.0 Ethernet controller: Silicon Integrated Systems [SiS]: Unknown device 0190
00: 39 10 90 01 07 00 10 02 00 00 00 02 00 00 00 00
10: 00 3c bf fe 01 d4 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 43 10 39 81
30: 00 00 00 00 40 00 00 00 00 00 00 00 05 01 00 00
40: 01 00 02 fe 00 00 00 00 00 00 00 00 00 00 00 00
50: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
70: 01 00 00 21 00 00 00 00 00 00 00 00 04 04 00 00
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00:05.0 RAID bus controller: Silicon Integrated Systems [SiS]: Unknown device 0182 (rev 01)
00: 39 10 82 01 05 00 10 02 01 85 04 01 00 40 00 00
10: 01 ec 00 00 01 e8 00 00 01 e4 00 00 01 e0 00 00
20: 01 dc 00 00 01 d8 00 00 00 00 00 00 43 10 39 81
30: 00 00 00 00 58 00 00 00 00 00 00 00 0b 01 00 00
40: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
50: a2 00 a2 00 2a 96 80 16 01 00 02 80 00 00 00 00
60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
80: bd 33 72 40 bd 33 72 40 bd 33 72 40 bd 33 72 40
90: 60 00 00 50 c0 05 c0 05 cc 04 0c 10 c0 05 c0 05
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 00 00 00 01 00 18 00 00 03 00 00 00 00 00 00
d0: 01 00 00 00 01 00 18 00 00 03 00 00 00 00 00 00
e0: 00 00 00 00 01 00 18 00 00 03 00 00 00 00 00 00
f0: 01 00 00 00 01 00 18 00 00 03 00 00 00 00 00 00
00:06.0 PCI bridge: Silicon Integrated Systems [SiS]: Unknown device 000a
00: 39 10 0a 00 06 01 10 00 00 00 04 06 10 00 01 00
10: 00 00 00 00 00 00 00 00 00 02 02 00 f1 01 00 00
20: f0 ff 00 00 f0 ff 00 00 00 00 00 00 00 00 00 00
30: 00 00 00 00 b0 00 00 00 00 00 00 00 00 00 07 00
40: 00 00 00 00 00 00 00 00 03 0a 80 00 00 00 00 00
50: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 0d c0 00 00 39 10 00 00 00 00 00 00 00 00 00 00
c0: 05 d0 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 10 f4 41 01 20 00 00 00 10 08 10 00 01 cd 00 00
e0: 00 00 01 10 00 00 00 00 c0 03 40 00 00 00 00 00
f0: 00 00 00 00 01 00 02 c8 00 00 00 00 00 00 00 00
00:07.0 PCI bridge: Silicon Integrated Systems [SiS]: Unknown device 000a
00: 39 10 0a 00 06 01 10 00 00 00 04 06 10 00 01 00
10: 00 00 00 00 00 00 00 00 00 03 03 00 f1 01 00 00
20: f0 ff 00 00 f0 ff 00 00 00 00 00 00 00 00 00 00
30: 00 00 00 00 b0 00 00 00 00 00 00 00 00 00 07 00
40: 00 00 00 00 00 00 00 00 03 0a 80 00 00 00 00 00
50: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 0d c0 00 00 39 10 00 00 00 00 00 00 00 00 00 00
c0: 05 d0 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 10 f4 41 01 20 00 00 00 10 08 10 00 01 cd 00 00
e0: 00 00 01 10 00 00 00 00 c0 03 40 00 00 00 00 00
f0: 00 00 00 00 01 00 02 c8 00 00 00 00 00 00 00 00
00:09.0 Ethernet controller: D-Link System Inc DL10050 Sundance Ethernet (rev 12)
00: 86 11 02 10 17 01 10 02 12 00 00 02 10 40 00 00
10: 01 d0 00 00 00 38 bf fe 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 86 11 02 10
30: 00 00 bd fe 50 00 00 00 00 00 00 00 05 01 0a 0a
40: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
50: 01 00 02 f6 00 40 00 00 00 00 00 00 00 00 00 00
60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00:18.0 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] HyperTransport Technology Configuration
00: 22 10 00 11 00 00 10 00 00 00 00 06 00 00 80 00
10: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
30: 00 00 00 00 80 00 00 00 00 00 00 00 00 00 00 00
40: 01 01 01 00 01 01 01 00 01 01 01 00 01 01 01 00
50: 01 01 01 00 01 01 01 00 01 01 01 00 01 01 01 00
60: 00 00 00 00 e4 00 00 00 0f cc 00 0f 1c 00 00 00
70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
80: 08 00 01 21 20 00 11 01 22 05 75 80 02 00 00 00
90: 56 04 51 02 00 00 ff 00 07 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00:18.1 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Address Map
00: 22 10 01 11 00 00 00 00 00 00 00 06 00 00 80 00
10: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
30: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
40: 03 00 00 00 00 00 1f 00 00 00 00 00 01 00 00 00
50: 00 00 00 00 02 00 00 00 00 00 00 00 03 00 00 00
60: 00 00 00 00 04 00 00 00 00 00 00 00 05 00 00 00
70: 00 00 00 00 06 00 00 00 00 00 00 00 07 00 00 00
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 03 0a 00 00 00 0b 00 00 03 00 20 00 00 ff ff 00
c0: 13 10 00 00 00 f0 ff 00 00 00 00 00 00 00 00 00
d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
e0: 03 00 00 ff 00 00 00 00 00 00 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00:18.2 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] DRAM Controller
00: 22 10 02 11 00 00 00 00 00 00 00 06 00 00 80 00
10: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
30: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
40: 01 00 00 00 01 00 00 01 00 00 00 00 00 00 00 00
50: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
60: 00 fe e0 00 00 fe e0 00 00 00 00 00 00 00 00 00
70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
80: 03 00 00 00 00 00 00 00 42 35 82 13 31 0b 00 00
90: 00 8c 0c 08 06 06 7b 3e 00 00 00 00 06 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: ff 68 ab 4a ed 00 00 00 39 e0 34 3a 00 7f f8 ff
c0: 00 00 01 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: b3 fa f9 50 3c e6 07 d6 92 de 71 66 70 dd f3 df
e0: db ba 7d ba 0c f2 17 23 db de 69 23 f0 6f 93 eb
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
00:18.3 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Miscellaneous Control
00: 22 10 03 11 00 00 00 00 00 00 00 06 00 00 80 00
10: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
30: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
40: ff 3b 00 00 40 00 40 00 00 00 00 00 00 00 00 00
50: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
60: 34 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
70: 11 01 02 51 11 80 00 50 00 38 00 08 1b 22 00 00
80: 00 00 07 23 13 21 13 21 00 00 00 00 00 00 00 00
90: 02 00 00 00 70 00 00 00 f0 ff ff bf 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 31 00 00 e0 ec 00 00 00
c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 00 00 00 00 01 07 0d 00 00 00 00 00 00 00 00 00
e0: 00 00 00 00 20 0c 48 00 08 01 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
01:00.0 VGA compatible controller: Silicon Integrated Systems [SiS] 661FX/M661FX/M661MX/741/M741/760/M760 PCI/AGP
00: 39 10 30 63 03 00 30 02 00 00 00 03 00 00 00 80
10: 08 00 00 f0 00 00 ae fe 01 cc 00 00 00 00 00 00
20: 00 00 00 00 00 00 00 00 00 00 00 00 43 10 59 81
30: 00 00 00 00 40 00 00 00 00 00 00 00 00 00 00 00
40: 01 50 02 06 00 00 00 00 00 00 00 00 00 00 00 00
50: 02 00 30 00 0b 02 00 ff 00 00 00 00 00 00 00 00
60: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
70: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
90: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
a0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
[-- Attachment #4: out.txt --]
[-- Type: text/plain, Size: 12890 bytes --]
00:00.0 Host bridge: Silicon Integrated Systems [SiS] 760/M760 Host (rev 03)
Subsystem: ASUSTeK Computer Inc.: Unknown device 8159
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66Mhz- UDF- FastB2B- ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort+ >SERR- <PERR-
Latency: 32
Region 0: Memory at e0000000 (32-bit, non-prefetchable) [size=64M]
Capabilities: [a0] AGP version 3.0
Status: RQ=32 Iso- ArqSz=2 Cal=3 SBA+ ITACoh- GART64- HTrans- 64bit- FW- AGP3+ Rate=x4,x8
Command: RQ=1 ArqSz=0 Cal=0 SBA+ AGP- GART64- 64bit- FW- Rate=<none>
Capabilities: [d0] HyperTransport: Slave or Primary Interface
!!! Possibly incomplete decoding
Command: BaseUnitID=0 UnitCnt=9 MastHost- DefDir-
Link Control 0: CFlE- CST- CFE- <LkFail- Init+ EOC+ TXO- <CRCErr=0
Link Config 0: MLWI=16bit MLWO=16bit LWI=8bit LWO=16bit
Link Control 1: CFlE- CST- CFE- <LkFail+ Init- EOC+ TXO+ <CRCErr=0
Link Config 1: MLWI=N/C MLWO=N/C LWI=N/C LWO=N/C
Revision ID: 1.02
Capabilities: [f0] HyperTransport: Interrupt Discovery and Configuration
00:01.0 PCI bridge: Silicon Integrated Systems [SiS] SG86C202 (prog-if 00 [Normal decode])
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap- 66Mhz+ UDF- FastB2B- ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 64
Bus: primary=00, secondary=01, subordinate=01, sec-latency=64
I/O behind bridge: 0000c000-0000cfff
Memory behind bridge: fea00000-feafffff
Prefetchable memory behind bridge: ee900000-fe8fffff
Secondary status: 66Mhz+ FastB2B- ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort+ <SERR- <PERR-
BridgeCtl: Parity- SERR+ NoISA- VGA+ MAbort- >Reset- FastB2B-
00:02.0 ISA bridge: Silicon Integrated Systems [SiS] SiS965 [MuTIOL Media IO] (rev 47)
Control: I/O+ Mem+ BusMaster+ SpecCycle+ MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap- 66Mhz- UDF- FastB2B- ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0
00:02.5 IDE interface: Silicon Integrated Systems [SiS] 5513 [IDE] (rev 01) (prog-if 80 [Master])
Subsystem: ASUSTeK Computer Inc.: Unknown device 8139
Control: I/O+ Mem- BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66Mhz- UDF- FastB2B- ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 128
Region 0: I/O ports at <unassigned>
Region 1: I/O ports at <unassigned>
Region 2: I/O ports at <unassigned>
Region 3: I/O ports at <unassigned>
Region 4: I/O ports at ffa0 [size=16]
Capabilities: [58] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0-,D1-,D2-,D3hot-,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
00:03.0 USB Controller: Silicon Integrated Systems [SiS] USB 1.0 Controller (rev 0f) (prog-if 10 [OHCI])
Subsystem: ASUSTeK Computer Inc.: Unknown device 8139
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV+ VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap- 66Mhz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 64 (20000ns max)
Interrupt: pin A routed to IRQ 169
Region 0: Memory at febf4000 (32-bit, non-prefetchable) [size=4K]
00:03.1 USB Controller: Silicon Integrated Systems [SiS] USB 1.0 Controller (rev 0f) (prog-if 10 [OHCI])
Subsystem: ASUSTeK Computer Inc.: Unknown device 8139
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV+ VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap- 66Mhz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 64 (20000ns max)
Interrupt: pin B routed to IRQ 177
Region 0: Memory at febf5000 (32-bit, non-prefetchable) [size=4K]
00:03.2 USB Controller: Silicon Integrated Systems [SiS] USB 1.0 Controller (rev 0f) (prog-if 10 [OHCI])
Subsystem: ASUSTeK Computer Inc.: Unknown device 8139
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV+ VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap- 66Mhz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 64 (20000ns max)
Interrupt: pin C routed to IRQ 185
Region 0: Memory at febf6000 (32-bit, non-prefetchable) [size=4K]
00:03.3 USB Controller: Silicon Integrated Systems [SiS] USB 2.0 Controller (prog-if 20 [EHCI])
Subsystem: ASUSTeK Computer Inc.: Unknown device 8139
Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap+ 66Mhz- UDF- FastB2B+ ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 64 (20000ns max)
Interrupt: pin D routed to IRQ 193
Region 0: Memory at febf7000 (32-bit, non-prefetchable) [size=4K]
Capabilities: [50] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=375mA PME(D0+,D1-,D2-,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
00:04.0 Ethernet controller: Silicon Integrated Systems [SiS]: Unknown device 0190
Subsystem: ASUSTeK Computer Inc.: Unknown device 8139
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66Mhz- UDF- FastB2B- ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0
Interrupt: pin A routed to IRQ 201
Region 0: Memory at febf3c00 (32-bit, non-prefetchable) [size=128]
Region 1: I/O ports at d400 [size=128]
Capabilities: [40] Power Management version 2
Flags: PMEClk- DSI- D1+ D2+ AuxCurrent=0mA PME(D0+,D1+,D2+,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
00:05.0 RAID bus controller: Silicon Integrated Systems [SiS]: Unknown device 0182 (rev 01) (prog-if 85)
Subsystem: ASUSTeK Computer Inc.: Unknown device 8139
Control: I/O+ Mem- BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66Mhz- UDF- FastB2B- ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 64
Interrupt: pin A routed to IRQ 209
Region 0: I/O ports at ec00 [size=8]
Region 1: I/O ports at e800 [size=4]
Region 2: I/O ports at e400 [size=8]
Region 3: I/O ports at e000 [size=4]
Region 4: I/O ports at dc00 [size=16]
Region 5: I/O ports at d800 [size=128]
Capabilities: [58] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0-,D1-,D2-,D3hot-,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
00:06.0 PCI bridge: Silicon Integrated Systems [SiS]: Unknown device 000a (prog-if 00 [Normal decode])
Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap+ 66Mhz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0, Cache Line Size 10
Bus: primary=00, secondary=02, subordinate=02, sec-latency=0
I/O behind bridge: 0000f000-00000fff
Memory behind bridge: fff00000-000fffff
Prefetchable memory behind bridge: fff00000-000fffff
Secondary status: 66Mhz- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- <SERR- <PERR-
BridgeCtl: Parity+ SERR+ NoISA+ VGA- MAbort- >Reset- FastB2B-
Capabilities: [b0] #0d [0000]
Capabilities: [c0] Message Signalled Interrupts: 64bit- Queue=0/0 Enable-
Address: 00000000 Data: 0000
Capabilities: [d0] Express Root Port (Slot+) IRQ 0
Device: Supported: MaxPayload 128 bytes, PhantFunc 0, ExtTag+
Device: Latency L0s <64ns, L1 <1us
Device: Errors: Correctable- Non-Fatal- Fatal- Unsupported-
Device: RlxdOrd+ ExtTag- PhantFunc- AuxPwr- NoSnoop+
Device: MaxPayload 128 bytes, MaxReadReq 128 bytes
Link: Supported Speed 2.5Gb/s, Width x16, ASPM L0s L1, Port 0
Link: Latency L0s <1us, L1 <2us
Link: ASPM Disabled RCB 64 bytes CommClk- ExtSynch-
Link: Speed 2.5Gb/s, Width x16
Slot: AtnBtn- PwrCtrl- MRL- AtnInd- PwrInd- HotPlug- Surpise-
Slot: Number 0, PowerLimit 0.000000
Slot: Enabled AtnBtn- PwrFlt- MRL- PresDet- CmdCplt- HPIrq-
Slot: AttnInd Off, PwrInd Off, Power-
Root: Correctable- Non-Fatal- Fatal- PME-
Capabilities: [f4] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
00:07.0 PCI bridge: Silicon Integrated Systems [SiS]: Unknown device 000a (prog-if 00 [Normal decode])
Control: I/O- Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap+ 66Mhz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 0, Cache Line Size 10
Bus: primary=00, secondary=03, subordinate=03, sec-latency=0
I/O behind bridge: 0000f000-00000fff
Memory behind bridge: fff00000-000fffff
Prefetchable memory behind bridge: fff00000-000fffff
Secondary status: 66Mhz- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- <SERR- <PERR-
BridgeCtl: Parity+ SERR+ NoISA+ VGA- MAbort- >Reset- FastB2B-
Capabilities: [b0] #0d [0000]
Capabilities: [c0] Message Signalled Interrupts: 64bit- Queue=0/0 Enable-
Address: 00000000 Data: 0000
Capabilities: [d0] Express Root Port (Slot+) IRQ 0
Device: Supported: MaxPayload 128 bytes, PhantFunc 0, ExtTag+
Device: Latency L0s <64ns, L1 <1us
Device: Errors: Correctable- Non-Fatal- Fatal- Unsupported-
Device: RlxdOrd+ ExtTag- PhantFunc- AuxPwr- NoSnoop+
Device: MaxPayload 128 bytes, MaxReadReq 128 bytes
Link: Supported Speed 2.5Gb/s, Width x16, ASPM L0s L1, Port 0
Link: Latency L0s <1us, L1 <2us
Link: ASPM Disabled RCB 64 bytes CommClk- ExtSynch-
Link: Speed 2.5Gb/s, Width x16
Slot: AtnBtn- PwrCtrl- MRL- AtnInd- PwrInd- HotPlug- Surpise-
Slot: Number 0, PowerLimit 0.000000
Slot: Enabled AtnBtn- PwrFlt- MRL- PresDet- CmdCplt- HPIrq-
Slot: AttnInd Off, PwrInd Off, Power-
Root: Correctable- Non-Fatal- Fatal- PME-
Capabilities: [f4] Power Management version 2
Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA PME(D0+,D1-,D2-,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
00:09.0 Ethernet controller: D-Link System Inc DL10050 Sundance Ethernet (rev 12)
Subsystem: D-Link System Inc DFE-550TX
Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV+ VGASnoop- ParErr- Stepping- SERR+ FastB2B-
Status: Cap+ 66Mhz- UDF- FastB2B- ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Latency: 64 (2500ns min, 2500ns max), Cache Line Size 10
Interrupt: pin A routed to IRQ 217
Region 0: I/O ports at d000 [size=128]
Region 1: Memory at febf3800 (32-bit, non-prefetchable) [size=512]
Expansion ROM at febd0000 [disabled] [size=64K]
Capabilities: [50] Power Management version 2
Flags: PMEClk- DSI- D1+ D2+ AuxCurrent=0mA PME(D0-,D1+,D2+,D3hot+,D3cold+)
Status: D0 PME-Enable- DSel=0 DScale=2 PME-
00:18.0 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] HyperTransport Technology Configuration
Control: I/O- Mem- BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66Mhz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
Capabilities: [80] HyperTransport: Host or Secondary Interface
!!! Possibly incomplete decoding
Command: WarmRst+ DblEnd-
Link Control: CFlE- CST- CFE- <LkFail- Init+ EOC- TXO- <CRCErr=0
Link Config: MLWI=16bit MLWO=16bit LWI=16bit LWO=8bit
Revision ID: 1.02
00:18.1 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Address Map
Control: I/O- Mem- BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap- 66Mhz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
00:18.2 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] DRAM Controller
Control: I/O- Mem- BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap- 66Mhz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
00:18.3 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Miscellaneous Control
Control: I/O- Mem- BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap- 66Mhz- UDF- FastB2B- ParErr- DEVSEL=fast >TAbort- <TAbort- <MAbort- >SERR- <PERR-
01:00.0 VGA compatible controller: Silicon Integrated Systems [SiS] 661FX/M661FX/M661MX/741/M741/760/M760 PCI/AGP (prog-if 00 [VGA])
Subsystem: ASUSTeK Computer Inc.: Unknown device 8159
Control: I/O+ Mem+ BusMaster- SpecCycle- MemWINV- VGASnoop- ParErr- Stepping- SERR- FastB2B-
Status: Cap+ 66Mhz+ UDF- FastB2B- ParErr- DEVSEL=medium >TAbort- <TAbort- <MAbort- >SERR- <PERR-
BIST result: 00
Region 0: Memory at f0000000 (32-bit, prefetchable) [size=128M]
Region 1: Memory at feae0000 (32-bit, non-prefetchable) [size=128K]
Region 2: I/O ports at cc00 [size=128]
Capabilities: [40] Power Management version 2
Flags: PMEClk- DSI- D1+ D2+ AuxCurrent=0mA PME(D0-,D1-,D2-,D3hot-,D3cold-)
Status: D0 PME-Enable- DSel=0 DScale=0 PME-
Capabilities: [50] AGP version 3.0
Status: RQ=256 Iso- ArqSz=0 Cal=0 SBA+ ITACoh- GART64- HTrans- 64bit- FW- AGP3+ Rate=x4,x8
Command: RQ=1 ArqSz=0 Cal=0 SBA- AGP- GART64- 64bit- FW- Rate=<none>
^ permalink raw reply [flat|nested] 27+ messages in thread
* Re: sis190
2005-06-08 22:51 ` sis190 (was: Re: sis5513.c patch) Francois Romieu
@ 2005-06-09 4:54 ` Andrew Hutchings
2005-06-09 12:02 ` sis190 Andrew Hutchings
1 sibling, 0 replies; 27+ messages in thread
From: Andrew Hutchings @ 2005-06-09 4:54 UTC (permalink / raw)
To: Francois Romieu; +Cc: linux-kernel
Francois Romieu wrote:
> Patch of the day:
>
> http://www.fr.zoreil.com/people/francois/misc/20050609-2.6.12-rc-sis190-test.patch
>
> Apply against current 2.6.12-rc12
>
> I'll be surprized if it works. I'll appreciate to know when and how it
> breaks.
>
> --
> Ueimor
>
We have 2 boards in as production servers in Manchester now (we are
based in North Wales, about an hour and a half drive, or an hour if I am
driving) but I have 1 sitting on my workbench at work ready for the
kill, I'll build that today and try and kill it. I'll let you know what
happens.
Regards
Andrew
--
Andrew Hutchings (A-Wing)
Linux Guru - Netserve Consultants Ltd. - http://www.domaincity.co.uk/
Admin - North Wales Linux User Group - http://www.nwlug.org.uk/
BOFH excuse 426: internet is needed to catch the etherbunny
^ permalink raw reply [flat|nested] 27+ messages in thread
end of thread, other threads:[~2005-07-10 13:23 UTC | newest]
Thread overview: 27+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2005-06-15 15:22 sis190 Pascal CHAPPERON
2005-06-16 22:34 ` sis190 Francois Romieu
-- strict thread matches above, loose matches on Subject: below --
2005-07-10 13:23 sis190 Pascal CHAPPERON
2005-07-09 13:25 sis190 Pascal CHAPPERON
2005-07-09 20:57 ` sis190 Francois Romieu
2005-07-06 15:58 sis190 Pascal CHAPPERON
2005-07-06 21:29 ` sis190 Francois Romieu
2005-07-02 10:52 sis190 Pascal CHAPPERON
2005-07-02 11:33 ` sis190 Francois Romieu
2005-07-04 23:30 ` sis190 Francois Romieu
2005-06-26 12:39 sis190 Pascal CHAPPERON
2005-06-30 23:37 ` sis190 Francois Romieu
2005-06-19 10:17 sis190 Pascal CHAPPERON
2005-06-21 23:02 ` sis190 Francois Romieu
2005-06-17 11:14 sis190 Pascal CHAPPERON
2005-06-17 18:22 ` sis190 Francois Romieu
2005-06-14 14:14 sis190 Pascal CHAPPERON
2005-06-14 20:04 ` sis190 Francois Romieu
2005-06-13 8:19 sis190 Pascal CHAPPERON
2005-06-13 21:39 ` sis190 Francois Romieu
2005-06-11 9:39 sis190 Pascal CHAPPERON
2005-06-11 10:56 ` sis190 Francois Romieu
2005-06-07 22:37 sis5513.c patch Andrew Hutchings
2005-06-07 22:57 ` Francois Romieu
2005-06-07 23:20 ` Andrew Hutchings
2005-06-08 22:51 ` sis190 (was: Re: sis5513.c patch) Francois Romieu
2005-06-09 4:54 ` sis190 Andrew Hutchings
2005-06-09 12:02 ` sis190 Andrew Hutchings
2005-06-09 21:18 ` sis190 Francois Romieu
2005-06-10 13:55 ` sis190 Andrew Hutchings
2005-06-10 23:41 ` sis190 Francois Romieu
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).